Yuxin Peng

Ting Lei, Fabian Caba, Qingchao Chen et al.

Human Object Interaction (HOI) detection aims to localize and infer the relationships between a human and an object. Arguably, training supervised models for this task from scratch presents challenges due to the performance drop over rare classes and the high computational cost and time required to handle long-tailed distributions of HOIs in complex HOI scenes in realistic settings. This observation motivates us to design an HOI detector that can be trained even with long-tailed labeled data and can leverage existing knowledge from pre-trained models. Inspired by the powerful generalization ability of the large Vision-Language Models (VLM) on classification and retrieval tasks, we propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM). ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm. Its second mode incorporates an instance-aware adapter mechanism that can further efficiently boost performance if updating a lightweight set of parameters can be afforded. Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time. Code can be found at https://github.com/ltttpku/ADA-CM.

Peng Wu, Jing Liu, Xiangteng He et al.

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame level, which can be roughly interpreted as the binary or multiple event classification. However, such a setup that builds relationships between complicated anomalous events and single labels, e.g., ``vandalism'', is superficial, since single labels are deficient to characterize anomalous events. In reality, users tend to search a specific video rather than a series of approximate videos. Therefore, retrieving anomalous events using detailed descriptions is practical and positive but few researches focus on this. In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e.g., language descriptions and synchronous audios. Unlike the current video retrieval where videos are assumed to be temporally well-trimmed with short duration, VAR is devised to retrieve long untrimmed videos which may be partially relevant to the given query. To achieve this, we present two large-scale VAR benchmarks, UCFCrime-AR and XDViolence-AR, constructed on top of prevalent anomaly datasets. Meanwhile, we design a model called Anomaly-Led Alignment Network (ALAN) for VAR. In ALAN, we propose an anomaly-led sampling to focus on key segments in long untrimmed videos. Then, we introduce an efficient pretext task to enhance semantic associations between video-text fine-grained representations. Besides, we leverage two complementary alignments to further match cross-modal contents. Experimental results on two benchmarks reveal the challenges of VAR task and also demonstrate the advantages of our tailored method. Captions are publicly released at https://github.com/Roc-Ng/VAR.

Hongbo Sun, Xiangteng He, Yuxin Peng

Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention mechanism research for discriminative regions mining while neglecting their interdependencies and composed holistic object structure, which are essential for model's discriminative information localization and understanding ability. To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object structure information into transformer for enhancing discriminative representation learning to contain both the appearance information and structure information. Specifically, we encode the image into a sequence of patch tokens and build a strong vision transformer framework with two well-designed modules: (i) the structure information learning (SIL) module is proposed to mine the spatial context relation of significant patches within the object extent with the help of the transformer's self-attention weights, which is further injected into the model for importing structure information; (ii) the multi-level feature boosting (MFB) module is introduced to exploit the complementary of multi-level features and contrastive learning among classes to enhance feature robustness for accurate recognition. The proposed two modules are light-weighted and can be plugged into any transformer network and trained end-to-end easily, which only depends on the attention weights that come with the vision transformer itself. Extensive experiments and analyses demonstrate that the proposed SIM-Trans achieves state-of-the-art performance on fine-grained visual categorization benchmarks. The code is available at https://github.com/PKU-ICST-MIPL/SIM-Trans_ACMMM2022.

Yulin Pan, Xiangteng He, Biao Gong et al.

Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\textit{e.g.}, in minutes), temporal grounding in long videos (\textit{e.g.}, in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with \textbf{one-time} network execution. Our pipeline is formulated in a coarse-to-fine manner, where we first extract context knowledge from non-overlapped video clips (\textit{i.e.}, anchors), and then supplement the anchors that highly response to the query with detailed content knowledge. Besides the remarkably high pipeline efficiency, another advantage of our approach is the capability of capturing long-range temporal correlation, thanks to modeling the entire video as a whole, and hence facilitates more accurate grounding. Experimental results suggest that, on the long-form video datasets MAD and Ego4d, our method significantly outperforms state-of-the-arts, and achieves \textbf{14.6$\times$} / \textbf{102.8$\times$} higher efficiency respectively. Project can be found at \url{https://github.com/afcedf/SOONet.git}.

Minghang Zheng, Jiahua Zhang, Qingchao Chen et al.

Visual grounding aims to localize the object referred to in an image based on a natural language query. Although progress has been made recently, accurately localizing target objects within multiple-instance distractions (multiple objects of the same category as the target) remains a significant challenge. Existing methods demonstrate a significant performance drop when there are multiple distractions in an image, indicating an insufficient understanding of the fine-grained semantics and spatial relationships between objects. In this paper, we propose a novel approach, the Relation and Semantic-sensitive Visual Grounding (ResVG) model, to address this issue. Firstly, we enhance the model's understanding of fine-grained semantics by injecting semantic prior information derived from text queries into the model. This is achieved by leveraging text-to-image generation models to produce images representing the semantic attributes of target objects described in queries. Secondly, we tackle the lack of training samples with multiple distractions by introducing a relation-sensitive data augmentation method. This method generates additional training data by synthesizing images containing multiple objects of the same category and pseudo queries based on their spatial relationships. The proposed ReSVG model significantly improves the model's ability to comprehend both object semantics and spatial relations, leading to enhanced performance in visual grounding tasks, particularly in scenarios with multiple-instance distractions. We conduct extensive experiments to validate the effectiveness of our methods on five datasets. Code is available at https://github.com/minghangz/ResVG.

Ting Lei, Shaofeng Yin, Yuxin Peng et al.

Zero-shot Human-Object Interaction (HOI) detection has emerged as a frontier topic due to its capability to detect HOIs beyond a predefined set of categories. This task entails not only identifying the interactiveness of human-object pairs and localizing them but also recognizing both seen and unseen interaction categories. In this paper, we introduce a novel framework for zero-shot HOI detection using Conditional Multi-Modal Prompts, namely CMMP. This approach enhances the generalization of large foundation models, such as CLIP, when fine-tuned for HOI detection. Unlike traditional prompt-learning methods, we propose learning decoupled vision and language prompts for interactiveness-aware visual feature extraction and generalizable interaction classification, respectively. Specifically, we integrate prior knowledge of different granularity into conditional vision prompts, including an input-conditioned instance prior and a global spatial pattern prior. The former encourages the image encoder to treat instances belonging to seen or potentially unseen HOI concepts equally while the latter provides representative plausible spatial configuration of the human and object under interaction. Besides, we employ language-aware prompt learning with a consistency constraint to preserve the knowledge of the large foundation model to enable better generalization in the text branch. Extensive experiments demonstrate the efficacy of our detector with conditional multi-modal prompts, outperforming previous state-of-the-art on unseen classes of various zero-shot settings. The code and models are available at \url{https://github.com/ltttpku/CMMP}.

Xiu-Shen Wei, He-Yang Xu, Faen Zhang et al.

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this problem comprises. In this paper, we propose a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective, and then augment the extremely label-constrained support set in few-shot classification tasks. Our approach can be implemented in just few lines of code by only using off-the-shelf operations, yet it is able to outperform state-of-the-art methods on four benchmark datasets.

Minghang Zheng, Zihao Yin, Yi Yang et al.

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To overcome these limitations, we introduce OmniVTG, a new large-scale dataset for open-world VTG, coupled with a Self-Correction Chain-of-Thought (CoT) training paradigm designed to enhance the grounding capabilities of Multimodal Large Language Models (MLLMs). Our OmniVTG is constructed via a novel Semantic Coverage Iterative Expansion pipeline, which first identifies gaps in the vocabulary of existing datasets and collects videos that are highly likely to contain these target concepts. For high-quality annotation, we leverage the insight that modern MLLMs excel at dense captioning more than direct grounding and design a caption-centric data engine to prompt MLLMs to generate dense, timestamped descriptions. Beyond the dataset, we observe that simple supervised finetuning (SFT) is insufficient, as a performance gap between rare and common concepts still persists. We find that MLLMs' video understanding ability significantly surpasses their direct grounding ability. Based on this, we propose a Self-Correction Chain-of-Thought (CoT) training paradigm. We train the MLLM to first predict, then use its understanding capabilities to reflect on and refine its own predictions. This capability is instilled via a three-stage pipeline of SFT, CoT finetuning, and reinforcement learning. Extensive experiments show our approach not only excels at open-world grounding in our OmniVTG dataset but also achieves state-of-the-art zero-shot performance on four existing VTG benchmarks. Code is available at https://github.com/oceanflowlab/OmniVTG.

Xiu-Shen Wei, Yang Shen, Xuhao Sun et al.

Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to alleviate the challenges of both fine-grained nature of small inter-class variations with large intra-class variations and explosive growth of fine-grained data for such a practical task. In this paper, we propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations. Our models are also equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities. Then, driven by preserving original entities' similarity, the required hash codes can be generated from these attribute-specific vectors and thus become attribute-aware. Furthermore, to combat simplicity bias in deep hashing, we consider the model design from the perspective of the self-consistency principle and propose to further enhance models' self-consistency by equipping an additional image reconstruction path. Comprehensive quantitative experiments under diverse empirical settings on six fine-grained retrieval datasets and two generic retrieval datasets show the superiority of our models over competing methods.

Tianxiang Du, Hulingxiao He, Yuxin Peng

In everyday photography, aesthetically appealing moments are often captured with structural flaws (e.g., composition, camera viewpoint, or pose) that existing retouching and portrait enhancement methods cannot fix. We formulate Aesthetic Photo Reconstruction (APR) as improving a photo's aesthetic quality via structural reconstruction while preserving subject identity and scene semantics. Although recent advances in image editing models make APR feasible, they often lack aesthetic understanding, yielding edits that are semantically plausible yet aesthetically weak. To address this, we propose AesFormer, a two-stage framework that decouples aesthetic planning from image editing. In Stage 1, an aesthetic action model (AesThinker) analyzes the input along seven progressive photographic dimensions and outputs executable editing actions; we further apply GRPO-A to encourage broad exploration over diverse action plans beyond SFT. In Stage 2, an action-conditioned editor (AesEditor) performs structural edits guided by these actions. To support APR, we build a video-based corpus-mining pipeline (VCMP) and construct AesRecon, a benchmark of 9,071 strictly aligned (poor, good) image pairs. Experiments show that AesFormer substantially improves APR performance and is competitive with Nano Banana Pro. Code is available at https://github.com/PKU-ICST-MIPL/AesFormer_ICML2026.

Haoran Feng, Yifan Niu, Zehuan Huang et al.

We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGen operates directly in the native 3D space, formulating layout generation as an autoregressive process that explicitly models geometric relations and physical constraints among objects, producing coherent and physically plausible 3D scenes. To further enhance this process, we propose an adapted 3D diffusion model that integrates scene, object, and instruction information and employs a dual-guidance self-rollout distillation mechanism to improve efficiency and spatial accuracy. Extensive experiments on the LayoutVLM benchmark show LaviGen achieves superior 3D layout generation performance, with 19% higher physical plausibility than the state of the art and 65% faster computation. Our code is publicly available at https://github.com/fenghora/LaviGen.

Hulingxiao He, Zijun Geng, Yuxin Peng

Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual tasks, they often struggle with Fine-Grained Visual Recognition (FGVR). Adapting general-purpose MLLMs to FGVR typically requires large amounts of annotated data, which is costly to obtain, leaving a substantial performance gap compared to contrastive CLIP models dedicated for discriminative tasks. Moreover, MLLMs tend to overfit to seen sub-categories and generalize poorly to unseen ones. To address these challenges, we propose Fine-R1, an MLLM tailored for FGVR through an R1-style training framework: (1) Chain-of-Thought Supervised Fine-tuning, where we construct a high-quality FGVR CoT dataset with rationales of "visual analysis, candidate sub-categories, comparison, and prediction", transition the model into a strong open-world classifier; and (2) Triplet Augmented Policy Optimization, where Intra-class Augmentation mixes trajectories from anchor and positive images within the same category to improve robustness to intra-class variance, while Inter-class Augmentation maximizes the response distinction conditioned on images across sub-categories to enhance discriminative ability. With only 4-shot training, Fine-R1 outperforms existing general MLLMs, reasoning MLLMs, and even contrastive CLIP models in identifying both seen and unseen sub-categories, showing promise in working in knowledge-intensive domains where gathering expert annotations for all sub-categories is arduous. Code is available at https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026.

HsiaoYuan Hsu, Xiangteng He, Yuxin Peng et al.

Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design. In practical applications, e.g., poster designs, the canvas is originally non-empty, and both inter-element relationships as well as inter-layer relationships should be concerned when generating a proper layout. A few recent works deal with them simultaneously, but they still suffer from poor graphic performance, such as a lack of layout variety or spatial non-alignment. Since content-aware visual-textual presentation layout is a novel task, we first construct a new dataset named PosterLayout, which consists of 9,974 poster-layout pairs and 905 images, i.e., non-empty canvases. It is more challenging and useful for greater layout variety, domain diversity, and content diversity. Then, we propose design sequence formation (DSF) that reorganizes elements in layouts to imitate the design processes of human designers, and a novel CNN-LSTM-based conditional generative adversarial network (GAN) is presented to generate proper layouts. Specifically, the discriminator is design-sequence-aware and will supervise the "design" process of the generator. Experimental results verify the usefulness of the new benchmark and the effectiveness of the proposed approach, which achieves the best performance by generating suitable layouts for diverse canvases.

Minghang Zheng, Dejie Yang, Zhongjie Ye et al.

In this technical report, we briefly introduce the solutions of our team `PKU-WICT-MIPL' for the PIC Makeup Temporal Video Grounding (MTVG) Challenge in ACM-MM 2022. Given an untrimmed makeup video and a step query, the MTVG aims to localize a temporal moment of the target makeup step in the video. To tackle this task, we propose a phrase relationship mining framework to exploit the temporal localization relationship relevant to the fine-grained phrase and the whole sentence. Besides, we propose to constrain the localization results of different step sentence queries to not overlap with each other through a dynamic programming algorithm. The experimental results demonstrate the effectiveness of our method. Our final submission ranked 2nd on the leaderboard, with only a 0.55\% gap from the first.

Minghang Zheng, Xinhao Cai, Qingchao Chen et al.

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data collection costs, but they exhibit poor generalization capability under the across-dataset and out-of-distribution (OOD) settings. In this paper, we propose a Training-Free Video Temporal Grounding (TFVTG) approach that leverages the ability of pre-trained large models. A naive baseline is to enumerate proposals in the video and use the pre-trained visual language models (VLMs) to select the best proposal according to the vision-language alignment. However, most existing VLMs are trained on image-text pairs or trimmed video clip-text pairs, making it struggle to (1) grasp the relationship and distinguish the temporal boundaries of multiple events within the same video; (2) comprehend and be sensitive to the dynamic transition of events (the transition from one event to another) in the video. To address these issues, we propose leveraging large language models (LLMs) to analyze multiple sub-events contained in the query text and analyze the temporal order and relationships between these events. Secondly, we split a sub-event into dynamic transition and static status parts and propose the dynamic and static scoring functions using VLMs to better evaluate the relevance between the event and the description. Finally, for each sub-event description, we use VLMs to locate the top-k proposals and leverage the order and relationships between sub-events provided by LLMs to filter and integrate these proposals. Our method achieves the best performance on zero-shot video temporal grounding on Charades-STA and ActivityNet Captions datasets without any training and demonstrates better generalization capabilities in cross-dataset and OOD settings.

Jinglin Xu, Yijie Guo, Yuxin Peng

The 3D Human Pose Estimation (3D HPE) task uses 2D images or videos to predict human joint coordinates in 3D space. Despite recent advancements in deep learning-based methods, they mostly ignore the capability of coupling accessible texts and naturally feasible knowledge of humans, missing out on valuable implicit supervision to guide the 3D HPE task. Moreover, previous efforts often study this task from the perspective of the whole human body, neglecting fine-grained guidance hidden in different body parts. To this end, we present a new Fine-Grained Prompt-Driven Denoiser based on a diffusion model for 3D HPE, named \textbf{FinePOSE}. It consists of three core blocks enhancing the reverse process of the diffusion model: (1) Fine-grained Part-aware Prompt learning (FPP) block constructs fine-grained part-aware prompts via coupling accessible texts and naturally feasible knowledge of body parts with learnable prompts to model implicit guidance. (2) Fine-grained Prompt-pose Communication (FPC) block establishes fine-grained communications between learned part-aware prompts and poses to improve the denoising quality. (3) Prompt-driven Timestamp Stylization (PTS) block integrates learned prompt embedding and temporal information related to the noise level to enable adaptive adjustment at each denoising step. Extensive experiments on public single-human pose estimation datasets show that FinePOSE outperforms state-of-the-art methods. We further extend FinePOSE to multi-human pose estimation. Achieving 34.3mm average MPJPE on the EgoHumans dataset demonstrates the potential of FinePOSE to deal with complex multi-human scenarios. Code is available at https://github.com/PKU-ICST-MIPL/FinePOSE_CVPR2024.

Jinglin Xu, Sibo Yin, Guohao Zhao et al.

Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer from low credibility and interpretability, thus insufficient for stringent applications, such as Olympic diving events. We argue that a fine-grained understanding of actions requires the model to perceive and parse actions in both time and space, which is also the key to the credibility and interpretability of the AQA technique. Based on this insight, we propose a new fine-grained spatial-temporal action parser named \textbf{FineParser}. It learns human-centric foreground action representations by focusing on target action regions within each frame and exploiting their fine-grained alignments in time and space to minimize the impact of invalid backgrounds during the assessment. In addition, we construct fine-grained annotations of human-centric foreground action masks for the FineDiving dataset, called \textbf{FineDiving-HM}. With refined annotations on diverse target action procedures, FineDiving-HM can promote the development of real-world AQA systems. Through extensive experiments, we demonstrate the effectiveness of FineParser, which outperforms state-of-the-art methods while supporting more tasks of fine-grained action understanding. Data and code are available at \url{https://github.com/PKU-ICST-MIPL/FineParser_CVPR2024}.

Huangbiao Xu, Huanqi Wu, Xiao Ke et al.

Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availability during training to provide reconstruction supervision or cross-modal priors. This paper tackles the more challenging setting of IML under training-time incomplete observations, which precludes reliance on a ``God's eye view'' of complete data. We propose LIMSSR (LLM-Driven Incomplete Multimodal Sequence-to-Score Reasoning), a framework that reformulates this challenge as a conditional sequence reasoning task. LIMSSR leverages the semantic reasoning capabilities of Large Language Models via Prompt-Guided Context-Aware Modality Imputation and Multidimensional Representation Fusion to infer latent semantics from available contexts without direct reconstruction. To mitigate hallucinations, we introduce a Mask-Aware Dual-Path Aggregation to dynamically calibrate inference uncertainty. Extensive experiments on three Action Quality Assessment datasets demonstrate that LIMSSR significantly outperforms state-of-the-art baselines without relying on complete training data, establishing a new paradigm for data-efficient multimodal learning. Code is available at https://github.com/XuHuangbiao/LIMSSR.

Zhiwen Yang, Yuxin Peng

Camera-based 3D semantic scene completion (SSC) offers a cost-effective solution for assessing the geometric occupancy and semantic labels of each voxel in the surrounding 3D scene with image inputs, providing a voxel-level scene perception foundation for the perception-prediction-planning autonomous driving systems. Although significant progress has been made in existing methods, their optimization rely solely on the supervision from voxel labels and face the challenge of voxel sparsity as a large portion of voxels in autonomous driving scenarios are empty, which limits both optimization efficiency and model performance. To address this issue, we propose a \textit{Multi-Resolution Alignment (MRA)} approach to mitigate voxel sparsity in camera-based 3D semantic scene completion, which exploits the scene and instance level alignment across multi-resolution 3D features as auxiliary supervision. Specifically, we first propose the Multi-resolution View Transformer module, which projects 2D image features into multi-resolution 3D features and aligns them at the scene level through fusing discriminative seed features. Furthermore, we design the Cubic Semantic Anisotropy module to identify the instance-level semantic significance of each voxel, accounting for the semantic differences of a specific voxel against its neighboring voxels within a cubic area. Finally, we devise a Critical Distribution Alignment module, which selects critical voxels as instance-level anchors with the guidance of cubic semantic anisotropy, and applies a circulated loss for auxiliary supervision on the critical feature distribution consistency across different resolutions. The code is available at https://github.com/PKU-ICST-MIPL/MRA_TIP.

He-Yang Xu, Pengyuan Zhang, Zongyuan Ge et al.

Fine-grained manipulation marks a regime where global scene context no longer suffices, and success hinges on the tight coupling of local attribute grounding, high-fidelity spatial perception, and constraint-respecting motor execution. However, current embodied AI benchmarks collapse these capacities into binary success rates, systematically inflating reported capabilities by up to 70% and masking the architectural bottlenecks that impede real-world deployment. We introduce MetaFine, a diagnostic meta-evaluation framework that disentangles manipulation competency along three axes: understanding, perception, and controlled behavior. Built on a compositional task graph, MetaFine absorbs heterogeneous external benchmarks and reconstructs them into diagnostic scenarios of varying complexity under a unified protocol. Evaluating state-of-the-art vision-language-action (VLA) models through this lens exposes severe dimension-specific failures invisible to conventional metrics. Through targeted causal intervention, we identify the visual encoder's ability to preserve local spatial structure as a key bottleneck for fine-grained precision: improving it directly unlocks previously inaccessible manipulation capabilities without modifying downstream policies. MetaFine further supports hybrid real-sim validation, using limited paired real-world rollouts to calibrate scalable simulation-based estimates for more stable physical benchmarking. By shifting evaluation from ranking to diagnosis, MetaFine turns benchmarking into an actionable compass for repairing the layered capacities underlying genuine physical dexterity. The MetaFine framework, benchmarks, and supporting resources will be publicly released at our project page: https://metafine.github.io/.

Geng Li, Jinglin Xu, Yunzhen Zhao et al.

Humans can effortlessly locate desired objects in cluttered environments, relying on a cognitive mechanism known as visual search to efficiently filter out irrelevant information and focus on task-related regions. Inspired by this process, we propose Dyfo (Dynamic Focus), a training-free dynamic focusing visual search method that enhances fine-grained visual understanding in large multimodal models (LMMs). Unlike existing approaches which require additional modules or data collection, Dyfo leverages a bidirectional interaction between LMMs and visual experts, using a Monte Carlo Tree Search (MCTS) algorithm to simulate human-like focus adjustments. This enables LMMs to focus on key visual regions while filtering out irrelevant content, without introducing additional training caused by vocabulary expansion or the integration of specialized localization modules. Experimental results demonstrate that Dyfo significantly improves fine-grained visual understanding and reduces hallucination issues in LMMs, achieving superior performance across both fixed and dynamic resolution models. The code is available at https://github.com/PKU-ICST-MIPL/DyFo_CVPR2025

Hulingxiao He, Geng Li, Zijun Geng et al.

Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories from images. This can negatively impact more advanced capabilities of MLLMs, such as object-centric visual question answering and reasoning. In our study, we revisit three quintessential capabilities of MLLMs for FGVR, including object information extraction, category knowledge reserve, object-category alignment, and position of the root cause as a misalignment problem. To address this issue, we present Finedefics, an MLLM that enhances the model's FGVR capability by incorporating informative attribute descriptions of objects into the training phase. We employ contrastive learning on object-attribute pairs and attribute-category pairs simultaneously and use examples from similar but incorrect categories as hard negatives, naturally bringing representations of visual objects and category names closer. Extensive evaluations across multiple popular FGVR datasets demonstrate that Finedefics outperforms existing MLLMs of comparable parameter sizes, showcasing its remarkable efficacy. The code is available at https://github.com/PKU-ICST-MIPL/Finedefics_ICLR2025.

Kunlun Xu, Chenghao Jiang, Peixi Xiong et al.

Lifelong person re-identification (LReID) is an important but challenging task that suffers from catastrophic forgetting due to significant domain gaps between training steps. Existing LReID approaches typically rely on data replay and knowledge distillation to mitigate this issue. However, data replay methods compromise data privacy by storing historical exemplars, while knowledge distillation methods suffer from limited performance due to the cumulative forgetting of undistilled knowledge. To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong anti-forgetting capacity without storing any exemplars. Specifically, we introduce an exemplar-free LReID method called Distribution Rehearsing via Adaptive Style Kernel Learning (DASK). DASK includes a Distribution Rehearser Learning (DRL) mechanism that learns to transform arbitrary distribution data into the current data style at each learning step. To enhance the style transfer capacity of DRL, an Adaptive Kernel Prediction Network (AKPNet) is explored to achieve an instance-specific distribution adjustment. Additionally, we design a Distribution Rehearsing-driven LReID Training (DRRT) module, which rehearses old distribution based on the new data via the old AKPNet model, achieving effective new-old knowledge accumulation under a joint knowledge consolidation scheme. Experimental results show our DASK outperforms the existing methods by 3.6%-6.8% and 4.5%-6.5% on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025-LReID-DASK

Zichen Liu, Kunlun Xu, Bing Su et al.

Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts, but they typically rely on a single static prompt for all video sequences, overlooking the diverse temporal dynamics and spatial variations that exist across frames. This limitation significantly hinders the model's ability to capture essential temporal information for effective video understanding. To address this, we propose an integrated Spatial-TempOral dynamic Prompting (STOP) model which consists of two complementary modules, the intra-frame spatial prompting and inter-frame temporal prompting. Our intra-frame spatial prompts are designed to adaptively highlight discriminative regions within each frame by leveraging intra-frame attention and temporal variation, allowing the model to focus on areas with substantial temporal dynamics and capture fine-grained spatial details. Additionally, to highlight the varying importance of frames for video understanding, we further introduce inter-frame temporal prompts, dynamically inserting prompts between frames with high temporal variance as measured by frame similarity. This enables the model to prioritize key frames and enhances its capacity to understand temporal dependencies across sequences. Extensive experiments on various video benchmarks demonstrate that STOP consistently achieves superior performance against state-of-the-art methods. The code is available at https://github.com/zhoujiahuan1991/CVPR2025-STOP.

Zhenyu Cui, Jiahuan Zhou, Yuxin Peng

Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its main challenge is to avoid the catastrophic forgetting problem of old knowledge while training on new data. Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as "re-indexing". However, historical gallery data typically suffers from direct saving due to the data privacy issue and the high re-indexing costs for large-scale gallery images. As a result, it inevitably leads to incompatible retrieval between query features extracted by the updated model and gallery features extracted by those before the update, greatly impairing the re-identification performance. To tackle the above issue, this paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images. Therefore, RFL-ReID is more challenging than L-ReID, requiring continuous learning and balancing new and old knowledge in diverse streaming data, and making the features output by the new and old models compatible with each other. To this end, we propose a Bidirectional Continuous Compatible Representation (Bi-C2R) framework to continuously update the gallery features extracted by the old model to perform efficient L-ReID in a compatible manner. We verify our proposed Bi-C2R method through theoretical analysis and extensive experiments on multiple benchmarks, which demonstrate that the proposed method can achieve leading performance on both the introduced RFL-ReID task and the traditional L-ReID task.

Jiayi Gao, Zijin Yin, Changcheng Hua et al.

The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage. However, current methods have two limitations: 1) struggle to handle multi-subjects videos, failing to transfer specific subject motion; 2) struggle to preserve the diversity and accuracy of motion as transferring to subjects with varying shapes. To overcome these, we introduce \textbf{ConMo}, a zero-shot framework that disentangle and recompose the motions of subjects and camera movements. ConMo isolates individual subject and background motion cues from complex trajectories in source videos using only subject masks, and reassembles them for target video generation. This approach enables more accurate motion control across diverse subjects and improves performance in multi-subject scenarios. Additionally, we propose soft guidance in the recomposition stage which controls the retention of original motion to adjust shape constraints, aiding subject shape adaptation and semantic transformation. Unlike previous methods, ConMo unlocks a wide range of applications, including subject size and position editing, subject removal, semantic modifications, and camera motion simulation. Extensive experiments demonstrate that ConMo significantly outperforms state-of-the-art methods in motion fidelity and semantic consistency. The code is available at https://github.com/Andyplus1/ConMo.

Yifeng Yao, Zichen Liu, Zhenyu Cui et al.

Pre-trained Vision Mamba (Vim) models have demonstrated exceptional performance across various computer vision tasks in a computationally efficient manner, attributed to their unique design of selective state space models. To further extend their applicability to diverse downstream vision tasks, Vim models can be adapted using the efficient fine-tuning technique known as visual prompting. However, existing visual prompting methods are predominantly tailored for Vision Transformer (ViT)-based models that leverage global attention, neglecting the distinctive sequential token-wise compression and propagation characteristics of Vim. Specifically, existing prompt tokens prefixed to the sequence are insufficient to effectively activate the input and forget gates across the entire sequence, hindering the extraction and propagation of discriminative information. To address this limitation, we introduce a novel Selective Visual Prompting (SVP) method specifically for the efficient fine-tuning of Vim. To prevent the loss of discriminative information during state space propagation, SVP employs lightweight selective prompters for token-wise prompt generation, ensuring adaptive activation of the update and forget gates within Mamba blocks to promote discriminative information propagation. Moreover, considering that Vim propagates both shared cross-layer information and specific inner-layer information, we further refine SVP with a dual-path structure: Cross-Prompting and Inner-Prompting. Cross-Prompting utilizes shared parameters across layers, while Inner-Prompting employs distinct parameters, promoting the propagation of both shared and specific information, respectively. Extensive experimental results on various large-scale benchmarks demonstrate that our proposed SVP significantly outperforms state-of-the-art methods. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025-SVP.

Chenyu Zhang, Kunlun Xu, Zichen Liu et al.

Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as a promising approach to enhance VLM performance under such conditions. In practice, test data often arrives in batches, leading to increasing interest in the transductive TTA setting. However, existing TTA methods primarily focus on individual test samples, overlooking crucial cross-sample correlations within a batch. While recent ViT-based TTA methods have introduced batch-level adaptation, they remain suboptimal for VLMs due to inadequate integration of the text modality. To address these limitations, we propose a novel transductive TTA framework, Supportive Clique-based Attribute Prompting (SCAP), which effectively combines visual and textual information to enhance adaptation by generating fine-grained attribute prompts across test batches. SCAP first forms supportive cliques of test samples in an unsupervised manner based on visual similarity and learns an attribute prompt for each clique, capturing shared attributes critical for adaptation. For each test sample, SCAP aggregates attribute prompts from its associated cliques, providing enriched contextual information. To ensure adaptability over time, we incorporate a retention module that dynamically updates attribute prompts and their associated attributes as new data arrives. Comprehensive experiments across multiple benchmarks demonstrate that SCAP outperforms existing state-of-the-art methods, significantly advancing VLM generalization under domain shifts. Our code is available at https://github.com/zhoujiahuan1991/CVPR2025-SCAP.

Hong-Tao Yu, Xiu-Shen Wei, Yuxin Peng et al.

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluation studies have emerged, assessing LVLMs both holistically and on specialized tasks, fine-grained image tasks-fundamental to computer vision-remain largely unexplored. To fill this gap, we introduce a comprehensive fine-grained evaluation benchmark, i.e., FG-BMK, comprising 1.01 million questions and 0.33 million images. Our evaluation systematically examines LVLMs from both human-oriented and machine-oriented perspectives, focusing on their semantic recognition and fine-grained feature representation capabilities. Through extensive experiments on twelve representative LVLMs/VLMs, we uncover key findings regarding the influence of training paradigms, modality alignment, perturbation susceptibility, and fine-grained category reasoning on task performance. This work provides critical insights into the limitations of current LVLMs and offers guidance for future data construction and model design in the development of more advanced LVLMs. Our code is open-source and available at https://github.com/SEU-VIPGroup/FG-BMK.

Zhuoying Li, Zhu Xu, Yuxin Peng et al.

Instruction-based image editing, which aims to modify the image faithfully according to the instruction while preserving irrelevant content unchanged, has made significant progress. However, there still lacks a comprehensive metric for assessing the editing quality. Existing metrics either require high human evaluation costs, which hinder large-scale evaluation, or are adapted from other tasks and lose task-specific concerns, failing to comprehensively evaluate both instruction-based modification and preservation of irrelevant regions, resulting in biased evaluation. To tackle this, we introduce a new metric called Balancing Preservation and Modification (BPM), tailored for instruction-based image editing by explicitly disentangling the image into editing-relevant and irrelevant regions for specific consideration. We first identify and locate editing-relevant regions, followed by a two-tier process to assess editing quality: Region-Aware Judge evaluates whether the position and size of the edited region align with the instruction, and Semantic-Aware Judge further assesses the instruction content compliance within editing-relevant regions as well as content preservation within irrelevant regions, yielding comprehensive and interpretable quality assessment. Moreover, the editing-relevant region localization in BPM can be integrated into image editing approaches to improve editing quality, demonstrating its broad applicability. We verify the effectiveness of the BPM metric on comprehensive instruction-editing data, and the results show the highest alignment with human evaluation compared to existing metrics, indicating its efficacy. Code is available at: https://joyli-x.github.io/BPM/

Geng Li, Yuxin Peng

Fine-grained recognition in everyday life is often not a closed-book classification problem: when encountering unfamiliar objects, humans actively search, compare visual details, and verify evidence before deciding. Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored. We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions. We introduce FIKA-Bench, a leakage-aware and evidence-grounded collection of 311 public-source and real-life instances. To ensure high quality, every example is filtered against frontier closed-book models to remove memorized cases and audited to eliminate image-answer leakage, retaining only samples supported by verified evidence. Our evaluation of latest Large Multimodal Models (LMMs) and agents reveals that the task remains a formidable challenge: the best system reaches only 25.1% accuracy, with no model exceeding 30%. Crucially, we find that merely equipping models with tools is insufficient to bridge this gap; agent failures are predominantly driven by wrong entity retrieval and poor visual judgement. These results show that reliable knowledge acquisition needs better agent designs that focus on fine-grained recognition.

Jiayi Gao, Changcheng Hua, Qingchao Chen et al.

Identity-preserving text-to-video (IPT2V) generation creates videos faithful to both a reference subject image and a text prompt. While fine-tuning large pretrained video diffusion models on ID-matched data achieves state-of-the-art results on IPT2V, data scarcity and high tuning costs hinder broader improvement. We thus introduce a Training-Free Prompt, Image, and Guidance Enhancement (TPIGE) framework that bridges the semantic gap between the video description and the reference image and design sampling guidance that enhances identity preservation and video quality, achieving performance gains at minimal cost.Specifically, we first propose Face Aware Prompt Enhancement, using GPT-4o to enhance the text prompt with facial details derived from the reference image. We then propose Prompt Aware Reference Image Enhancement, leveraging an identity-preserving image generator to refine the reference image, rectifying conflicts with the text prompt. The above mutual refinement significantly improves input quality before video generation. Finally, we propose ID-Aware Spatiotemporal Guidance Enhancement, utilizing unified gradients to optimize identity preservation and video quality jointly during generation.Our method outperforms prior work and is validated by automatic and human evaluations on a 1000 video test set, winning first place in the ACM Multimedia 2025 Identity-Preserving Video Generation Challenge, demonstrating state-of-the-art performance and strong generality. The code is available at https://github.com/Andyplus1/IPT2V.git.

Zhenyu Cui, Jiahuan Zhou, Yuxin Peng

Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong person Re-IDentification (VI-LReID) focuses on sequential training on data from visible and infrared modalities and pursues average performance over all data. To this end, existing methods typically exploit cross-modal knowledge distillation to alleviate the catastrophic forgetting of old knowledge. However, these methods ignore the mutual interference of modality-specific knowledge acquisition and modality-common knowledge anti-forgetting, where conflicting knowledge leads to collaborative forgetting. To address the above problems, this paper proposes a Cross-modality Knowledge Disentanglement and Alignment method, called CKDA, which explicitly separates and preserves modality-specific knowledge and modality-common knowledge in a balanced way. Specifically, a Modality-Common Prompting (MCP) module and a Modality-Specific Prompting (MSP) module are proposed to explicitly disentangle and purify discriminative information that coexists and is specific to different modalities, avoiding the mutual interference between both knowledge. In addition, a Cross-modal Knowledge Alignment (CKA) module is designed to further align the disentangled new knowledge with the old one in two mutually independent inter- and intra-modality feature spaces based on dual-modality prototypes in a balanced manner. Extensive experiments on four benchmark datasets verify the effectiveness and superiority of our CKDA against state-of-the-art methods. The source code of this paper is available at https://github.com/PKU-ICST-MIPL/CKDA-AAAI2026.

Zhiwen Yang, Yuxin Peng

Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems, assessing voxel-level geometry and semantics for holistic scene perception. While existing voxel-based and plane-based SSC methods have achieved considerable progress, they struggle to capture physical regularities for realistic geometric details. On the other hand, neural reconstruction methods like NeRF and 3DGS demonstrate superior physical awareness, but suffer from high computational cost and slow convergence when handling large-scale, complex autonomous driving scenes, leading to inferior semantic accuracy. To address these issues, we propose the Semantic-PHysical Engaged REpresentation (SPHERE) for camera-based SSC, which integrates voxel and Gaussian representations for joint exploitation of semantic and physical information. First, the Semantic-guided Gaussian Initialization (SGI) module leverages dual-branch 3D scene representations to locate focal voxels as anchors to guide efficient Gaussian initialization. Then, the Physical-aware Harmonics Enhancement (PHE) module incorporates semantic spherical harmonics to model physical-aware contextual details and promote semantic-geometry consistency through focal distribution alignment, generating SSC results with realistic details. Extensive experiments and analyses on the popular SemanticKITTI and SSCBench-KITTI-360 benchmarks validate the effectiveness of SPHERE. The code is available at https://github.com/PKU-ICST-MIPL/SPHERE_ACMMM2025.

Zhu Xu, Ting Lei, Zhimin Li et al.

Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an unlocalized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the-shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation-aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowledge Transferring (TRKT) method, which leverages knowledge to enhance detection in relation-aware dynamic scenarios. TRKT is built on two key components:(1)Relation-aware knowledge mining: we first employ object and relation class decoders that generate category-specific attention maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmentation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion-aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Action Genome dataset. Our code is avaliable at https://github.com/XZPKU/TRKT.git.

Minghang Zheng, Yuxin Peng, Benyuan Sun et al.

In this paper, we tackle the task of online video temporal grounding (OnVTG), which requires the model to locate events related to a given text query within a video stream. Unlike regular video temporal grounding, OnVTG requires the model to make predictions without observing future frames. As online videos are streaming inputs and can go on indefinitely, it is impractical and inefficient to store all historical inputs. The existing OnVTG models employ memory to store recent historical video frame features and predict scores indicating whether the current frame corresponds to the start or end time of the target event. However, these methods lack effective event modeling and cannot retain long-term historical information, leading to low performance. To tackle these challenges, we propose a hierarchical event memory for OnVTG. We propose an event-based OnVTG framework that makes predictions based on event proposals that model event-level information with various durations. To preserve historically valuable event information, we introduce a hierarchical event memory that retains historical events, allowing the model to access both recent and long-term information. To enable the real-time prediction, we further propose a future prediction branch that predicts whether the target event will occur shortly and further regresses the start time of the event. We achieve state-of-the-art performance on the TACoS, ActivityNet Captions, and MAD datasets. Code is available at https://github.com/minghangz/OnVTG.

Ting Lei, Shaofeng Yin, Qingchao Chen et al.

Open Vocabulary Human-Object Interaction (HOI) detection aims to detect interactions between humans and objects while generalizing to novel interaction classes beyond the training set. Current methods often rely on Vision and Language Models (VLMs) but face challenges due to suboptimal image encoders, as image-level pre-training does not align well with the fine-grained region-level interaction detection required for HOI. Additionally, effectively encoding textual descriptions of visual appearances remains difficult, limiting the model's ability to capture detailed HOI relationships. To address these issues, we propose INteraction-aware Prompting with Concept Calibration (INP-CC), an end-to-end open-vocabulary HOI detector that integrates interaction-aware prompts and concept calibration. Specifically, we propose an interaction-aware prompt generator that dynamically generates a compact set of prompts based on the input scene, enabling selective sharing among similar interactions. This approach directs the model's attention to key interaction patterns rather than generic image-level semantics, enhancing HOI detection. Furthermore, we refine HOI concept representations through language model-guided calibration, which helps distinguish diverse HOI concepts by investigating visual similarities across categories. A negative sampling strategy is also employed to improve inter-modal similarity modeling, enabling the model to better differentiate visually similar but semantically distinct actions. Extensive experimental results demonstrate that INP-CC significantly outperforms state-of-the-art models on the SWIG-HOI and HICO-DET datasets. Code is available at https://github.com/ltttpku/INP-CC.

Zixiang Ai, Zhenyu Cui, Yuxin Peng et al.

Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in real scenarios due to casual object occlusions and unsatisfactory data collected by 3D sensors. To this end, existing methods focus on enhancing point cloud quality by developing dedicated denoising and completion models. However, due to the isolation between the point cloud enhancement and downstream tasks, these methods fail to work in various real-world domains. In addition, the conflicting objectives between denoising and completing tasks further limit the ensemble paradigm to preserve critical geometric features. To tackle the above challenges, we propose a unified point-level prompting method that reformulates point cloud denoising and completion as a prompting mechanism, enabling robust analysis in a parameter-efficient manner. We start by introducing a Rectification Prompter to adapt to noisy points through the predicted rectification vector prompts, effectively filtering noise while preserving intricate geometric features essential for accurate analysis. Sequentially, we further incorporate a Completion Prompter to generate auxiliary point prompts based on the rectified point clouds, facilitating their robustness and adaptability. Finally, a Shape-Aware Unit module is exploited to efficiently unify and capture the filtered geometric features for the downstream point cloud analysis.Extensive experiments on four datasets demonstrate the superiority and robustness of our method when handling noisy and incomplete point cloud data against existing state-of-the-art methods. Our code is released at https://github.com/zhoujiahuan1991/ICCV2025-UPP.

Xiangteng He, Yuxin Peng, Liu Xie

Cross-media retrieval is to return the results of various media types corresponding to the query of any media type. Existing researches generally focus on coarse-grained cross-media retrieval. When users submit an image of "Slaty-backed Gull" as a query, coarse-grained cross-media retrieval treats it as "Bird", so that users can only get the results of "Bird", which may include other bird species with similar appearance (image and video), descriptions (text) or sounds (audio), such as "Herring Gull". Such coarse-grained cross-media retrieval is not consistent with human lifestyle, where we generally have the fine-grained requirement of returning the exactly relevant results of "Slaty-backed Gull" instead of "Herring Gull". However, few researches focus on fine-grained cross-media retrieval, which is a highly challenging and practical task. Therefore, in this paper, we first construct a new benchmark for fine-grained cross-media retrieval, which consists of 200 fine-grained subcategories of the "Bird", and contains 4 media types, including image, text, video and audio. To the best of our knowledge, it is the first benchmark with 4 media types for fine-grained cross-media retrieval. Then, we propose a uniform deep model, namely FGCrossNet, which simultaneously learns 4 types of media without discriminative treatments. We jointly consider three constraints for better common representation learning: classification constraint ensures the learning of discriminative features, center constraint ensures the compactness characteristic of the features of the same subcategory, and ranking constraint ensures the sparsity characteristic of the features of different subcategories. Extensive experiments verify the usefulness of the new benchmark and the effectiveness of our FGCrossNet. They will be made available at https://github.com/PKU-ICST-MIPL/FGCrossNet_ACMMM2019.

Kuoye Niu, Jianwei Li, Shengze Cai et al.

Multimodal resources for non-periodic court sports with laboratory-grade sensing remain scarce: few publicly pair instrumented ground reaction force (GRF) with high-frame-rate multi-view video, limiting markerless load estimation in realistic training settings. BadmintonGRF records eight synchronized RGB views at ~120 FPS, four Kistler force plates, and Vicon motion capture (C3D) without hardware genlock across modalities; alignment combines human-verified events, automated quality assurance, and per-camera time offsets with uncertainty metadata. Tier 1 distributes pose, time-aligned GRF, metadata, and splits under CC BY-NC 4.0, enabling the primary benchmark without raw RGB or C3D; we report a Tier 1 task that maps 2D pose to GRF. Tier 2 provides raw RGB and C3D under controlled access for studies that require appearance or full kinematics. The public release contains 17,425 impact-segment archives in the 10-subject benchmark tree (156 instrumented trials; raw multi-view RGB alone exceeds 1 TB); benchmark loader gates retain 12,867 view-specific instances and 1,732 unique impacts after multi-view deduplication. We are not aware of prior public badminton corpora that combine this sensing layout with audited video--GRF alignment for impact-centric GRF estimation. We distribute preprocessing code, leave-one-subject-out splits, ten reference baselines, and optional late fusion (one deterministic test-time pass per instance; no test-time augmentation), with a within-trial diagnostic in the supplementary material.

Xiangtian Zheng, Zishuo Wang, Yuxin Peng

With the rapid development of Large Language Models (LLMs), Video Multi-Modal Large Language Models (Video MLLMs) have achieved remarkable performance in video-language tasks such as video understanding and question answering. However, Video MLLMs face high computational costs, particularly in processing numerous video frames as input, which leads to significant attention computation overhead. A straightforward approach to reduce computational costs is to decrease the number of input video frames. However, simply selecting key frames at a fixed frame rate (FPS) often overlooks valuable information in non-key frames, resulting in notable performance degradation. To address this, we propose Text-guided Video Frame Reduction (TiFRe), a framework that reduces input frames while preserving essential video information. TiFRe uses a Text-guided Frame Sampling (TFS) strategy to select key frames based on user input, which is processed by an LLM to generate a CLIP-style prompt. Pre-trained CLIP encoders calculate the semantic similarity between the prompt and each frame, selecting the most relevant frames as key frames. To preserve video semantics, TiFRe employs a Frame Matching and Merging (FMM) mechanism, which integrates non-key frame information into the selected key frames, minimizing information loss. Experiments show that TiFRe effectively reduces computational costs while improving performance on video-language tasks.

Zhiwen Yang, Yuxin Peng

Camera-based 3D semantic scene completion (SSC) plays a crucial role in autonomous driving, enabling voxelized 3D scene understanding for effective scene perception and decision-making. Existing SSC methods have shown efficacy in improving 3D scene representations, but suffer from the inherent input-output dimension gap and annotation-reality density gap, where the 2D planner view from input images with sparse annotated labels leads to inferior prediction of real-world dense occupancy with a 3D stereoscopic view. In light of this, we propose the corresponding High-Dimension High-Density Semantic Scene Completion (HD$^2$-SSC) framework with expanded pixel semantics and refined voxel occupancies. To bridge the dimension gap, a High-dimension Semantic Decoupling module is designed to expand 2D image features along a pseudo third dimension, decoupling coarse pixel semantics from occlusions, and then identify focal regions with fine semantics to enrich image features. To mitigate the density gap, a High-density Occupancy Refinement module is devised with a "detect-and-refine" architecture to leverage contextual geometric and semantic structures for enhanced semantic density with the completion of missing voxels and correction of erroneous ones. Extensive experiments and analyses on the SemanticKITTI and SSCBench-KITTI-360 datasets validate the effectiveness of our HD$^2$-SSC framework.

Jiadong Pan, Liang Li, Yuxin Peng et al.

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a persistent capability gap exists: UMMs typically exhibit superior visual understanding but comparatively weaker generative capabilities. This discrepancy arises largely from the intrinsic decoupling between the understanding and generation processes. While a UMM can accurately interpret fine-grained visual details, it often struggles to produce semantically coherent images from complex textual prompts. To address this challenge, we explore UMMs' internal understanding capability to enhance generation quality. We propose a token-level intrinsic text-image alignment reward mechanism, GvU, enabling the UMM to act simultaneously as teacher and student: it evaluates its own outputs using the understanding branch to guide the generations accordingly. Building upon this, we design a self-supervised reinforcement learning framework, allowing UMMs to iteratively improve their generation quality through understanding-based intrinsic reward signals--without reliance on external supervision. Experimental results show that our method substantially boosts UMMs' generation, which in turn strengthens their fine-grained visual understanding, narrowing the capability gap between UMMs' visual understanding and generation.

HsiaoYuan Hsu, Yuxin Peng

In poster design, content-aware layout generation is crucial for automatically arranging visual-textual elements on the given image. With limited training data, existing work focused on image-centric enhancement. However, this neglects the diversity of layouts and fails to cope with shape-variant elements or diverse design intents in generalized settings. To this end, we proposed a layout-centric approach that leverages layout knowledge implicit in large language models (LLMs) to create posters for omnifarious purposes, hence the name PosterO. Specifically, it structures layouts from datasets as trees in SVG language by universal shape, design intent vectorization, and hierarchical node representation. Then, it applies LLMs during inference to predict new layout trees by in-context learning with intent-aligned example selection. After layout trees are generated, we can seamlessly realize them into poster designs by editing the chat with LLMs. Extensive experimental results have demonstrated that PosterO can generate visually appealing layouts for given images, achieving new state-of-the-art performance across various benchmarks. To further explore PosterO's abilities under the generalized settings, we built PStylish7, the first dataset with multi-purpose posters and various-shaped elements, further offering a challenging test for advanced research.

Wentao Mo, Qingchao Chen, Yuxin Peng et al.

The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of objects in single viewpoint, and annotations often link instructions to single objects, missing richer contextual alignments between multiple objects. This significantly curtails the development of models capable of deep, multi-view 3D scene understanding over distant objects. To address these challenges, we introduce MV-ScanQA, a novel 3D question answering dataset where 68% of questions explicitly require integrating information from multiple views (compared to less than 7% in existing datasets), thereby rigorously testing multi-view compositional reasoning. To facilitate the training of models for such demanding scenarios, we present TripAlign dataset, a large-scale and low-cost 2D-3D-language pre-training corpus containing 1M <2D view, set of 3D objects, text> triplets that explicitly aligns groups of contextually related objects with text, providing richer, view-grounded multi-object multimodal alignment signals than previous single-object annotations. We further develop LEGO, a baseline method for the multi-view reasoning challenge in MV-ScanQA, transferring knowledge from pre-trained 2D LVLMs to 3D domain with TripAlign. Empirically, LEGO pre-trained on TripAlign achieves state-of-the-art performance not only on the proposed MV-ScanQA, but also on existing benchmarks for 3D dense captioning and question answering. Datasets and code are available at https://matthewdm0816.github.io/tripalign-mvscanqa.

Zhiao Feng, Xuewei Li, Junjie Yang et al.

Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity, trajectory deformation, and uneven pixel density. To tackle these issues, we propose SphereDrag, a novel panoramic editing framework utilizing spherical geometry knowledge for accurate and controllable editing. Specifically, adaptive reprojection (AR) uses adaptive spherical rotation to deal with discontinuity; great-circle trajectory adjustment (GCTA) tracks the movement trajectory more accurate; spherical search region tracking (SSRT) adaptively scales the search range based on spherical location to address uneven pixel density. Also, we construct PanoBench, a panoramic editing benchmark, including complex editing tasks involving multiple objects and diverse styles, which provides a standardized evaluation framework. Experiments show that SphereDrag gains a considerable improvement compared with existing methods in geometric consistency and image quality, achieving up to 10.5% relative improvement.

Zhu Xu, Zhaowen Wang, Yuxin Peng et al.

Compositional Customized Image Generation aims to customize multiple target concepts within generation content, which has gained attention for its wild application. Existing approaches mainly concentrate on the target entity's appearance preservation, while neglecting the fine-grained interaction control among target entities. To enable the model of such interaction control capability, we focus on human object interaction scenario and propose the task of Customized Human Object Interaction Image Generation(CHOI), which simultaneously requires identity preservation for target human object and the interaction semantic control between them. Two primary challenges exist for CHOI:(1)simultaneous identity preservation and interaction control demands require the model to decompose the human object into self-contained identity features and pose-oriented interaction features, while the current HOI image datasets fail to provide ideal samples for such feature-decomposed learning.(2)inappropriate spatial configuration between human and object may lead to the lack of desired interaction semantics. To tackle it, we first process a large-scale dataset, where each sample encompasses the same pair of human object involving different interactive poses. Then we design a two-stage model Interact-Custom, which firstly explicitly models the spatial configuration by generating a foreground mask depicting the interaction behavior, then under the guidance of this mask, we generate the target human object interacting while preserving their identities features. Furthermore, if the background image and the union location of where the target human object should appear are provided by users, Interact-Custom also provides the optional functionality to specify them, offering high content controllability. Extensive experiments on our tailored metrics for CHOI task demonstrate the effectiveness of our approach.

Zijing Zhao, Zhu Xu, Qingchao Chen et al.

As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited datasets, where the training and testing sets share the same distribution. In this paper, we consider the task of adapting indoor 3D object detectors from one dataset to another, presenting a comprehensive benchmark with ScanNet, SUN RGB-D and 3D Front datasets, as well as our newly proposed large-scale datasets ProcTHOR-OD and ProcFront generated by a 3D simulator. Since indoor point cloud datasets are collected and constructed in different ways, the object detectors are likely to overfit to specific factors within each dataset, such as point cloud quality, bounding box layout and instance features. We conduct experiments across datasets on different adaptation scenarios including synthetic-to-real adaptation, point cloud quality adaptation, layout adaptation and instance feature adaptation, analyzing the impact of different domain gaps on 3D object detectors. We also introduce several approaches to improve adaptation performances, providing baselines for domain adaptive indoor 3D object detection, hoping that future works may propose detectors with stronger generalization ability across domains. Our project homepage can be found in https://jeremyzhao1998.github.io/DAVoteNet-release/.

HsiaoYuan Hsu, Yuxin Peng

In AI-empowered poster design, content-aware layout generation is crucial for the on-image arrangement of visual-textual elements, e.g., logo, text, and underlay. To perceive the background images, existing work demanded a high parameter count that far exceeds the size of available training data, which has impeded the model's real-time performance and generalization ability. To address these challenges, we proposed a patch-level data summarization and augmentation approach, vividly named Scan-and-Print. Specifically, the scan procedure selects only the patches suitable for placing element vertices to perform fine-grained perception efficiently. Then, the print procedure mixes up the patches and vertices across two image-layout pairs to synthesize over 100% new samples in each epoch while preserving their plausibility. Besides, to facilitate the vertex-level operations, a vertex-based layout representation is introduced. Extensive experimental results on widely used benchmarks demonstrated that Scan-and-Print can generate visually appealing layouts with state-of-the-art quality while dramatically reducing computational bottleneck by 95.2%.

Ansong Li, Zhiyong Cheng, Fan Liu et al.

Session-based recommendation (SBR) has drawn increasingly research attention in recent years, due to its great practical value by only exploiting the limited user behavior history in the current session. Existing methods typically learn the session embedding at the item level, namely, aggregating the embeddings of items with or without the attention weights assigned to items. However, they ignore the fact that a user's intent on adopting an item is driven by certain factors of the item (e.g., the leading actors of an movie). In other words, they have not explored finer-granularity interests of users at the factor level to generate the session embedding, leading to sub-optimal performance. To address the problem, we propose a novel method called Disentangled Graph Neural Network (Disen-GNN) to capture the session purpose with the consideration of factor-level attention on each item. Specifically, we first employ the disentangled learning technique to cast item embeddings into the embedding of multiple factors, and then use the gated graph neural network (GGNN) to learn the embedding factor-wisely based on the item adjacent similarity matrix computed for each factor. Moreover, the distance correlation is adopted to enhance the independence between each pair of factors. After representing each item with independent factors, an attention mechanism is designed to learn user intent to different factors of each item in the session. The session embedding is then generated by aggregating the item embeddings with attention weights of each item's factors. To this end, our model takes user intents at the factor level into account to infer the user purpose in a session. Extensive experiments on three benchmark datasets demonstrate the superiority of our method over existing methods.