Cairong Zhao

Cairong Zhao, Yubin Wang, Xinyang Jiang et al.

Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning achieves excellent performance over in-domain data, it still faces the major challenge of generalizing to unseen classes and domains. Some existing prompt learning methods tackle this issue by adaptively generating different prompts for different tokens or domains but neglecting the ability of learned prompts to generalize to unseen domains. In this paper, we propose a novel prompt learning paradigm that directly generates \emph{domain invariant} prompt that can be generalized to unseen domains, called MetaPrompt. Specifically, a dual-modality prompt tuning network is proposed to generate prompts for input from both image and text modalities. With a novel asymmetric contrastive loss, the representation from the original pre-trained vision-language model acts as supervision to enhance the generalization ability of the learned prompt. More importantly, we propose a meta-learning-based prompt tuning algorithm that explicitly constrains the task-specific prompt tuned for one domain or class to also achieve good performance in another domain or class. Extensive experiments on 11 datasets for base-to-new generalization and 4 datasets for domain generalization demonstrate that our method consistently and significantly outperforms existing methods.

Wenli Sun, Xinyang Jiang, Shuguang Dou et al.

In recent years, person Re-identification (ReID) has rapidly progressed with wide real-world applications, but also poses significant risks of adversarial attacks. In this paper, we focus on the backdoor attack on deep ReID models. Existing backdoor attack methods follow an all-to-one or all-to-all attack scenario, where all the target classes in the test set have already been seen in the training set. However, ReID is a much more complex fine-grained open-set recognition problem, where the identities in the test set are not contained in the training set. Thus, previous backdoor attack methods for classification are not applicable for ReID. To ameliorate this issue, we propose a novel backdoor attack on deep ReID under a new all-to-unknown scenario, called Dynamic Triggers Invisible Backdoor Attack (DT-IBA). Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities. Specifically, an identity hashing network is proposed to first extract target identity information from a reference image, which is then injected into the benign images by image steganography. We extensively validate the effectiveness and stealthiness of the proposed attack on benchmark datasets, and evaluate the effectiveness of several defense methods against our attack.

Junyao Gao, Xinyang Jiang, Huishuai Zhang et al.

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by membership inference (MI) attack. Most of the existing MI attack algorithms focus on classification models, while Re-ID follows a totally different training and inference paradigm. Re-ID is a fine-grained recognition task with complex feature embedding, and model outputs commonly used by existing MI like logits and losses are not accessible during inference. Since Re-ID focuses on modelling the relative relationship between image pairs instead of individual semantics, we conduct a formal and empirical analysis which validates that the distribution shift of the inter-sample similarity between training and test set is a critical criterion for Re-ID membership inference. As a result, we propose a novel membership inference attack method based on the inter-sample similarity distribution. Specifically, a set of anchor images are sampled to represent the similarity distribution conditioned on a target image, and a neural network with a novel anchor selection module is proposed to predict the membership of the target image. Our experiments validate the effectiveness of the proposed approach on both the Re-ID task and conventional classification task.

Boshen Zhang, Yuxi Li, Yuanpeng Tu et al.

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well. In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modalities, including image classification (CIFAR, Clothing1M etc) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA.

Qingsong Zhao, Yi Wang, Shuguang Dou et al.

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative pairs for contrastive learning or posing tighter class separating margins. These methods do not exploit the similarity between different classes as they adhere to i.i.d. assumption in data. In this paper, we embrace the real-world data distribution setting that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty. As the gradient of the proposed method is roughly proportional to the uncertainty of the predicted likelihoods, we name it adaptive discriminative regularization (ADR), trained along with a standard cross entropy loss in classification. Extensive experiments demonstrate that it can yield consistent and non-trivial performance improvements in a variety of visual classification tasks (over 10 benchmarks). Furthermore, we find it is robust to long-tailed and noisy label data distribution. Its flexible design enables its compatibility with mainstream classification architectures and losses.

Shuguang Dou, Xinyang Jiang, Qingsong Zhao et al.

Recently privacy concerns of person re-identification (ReID) raise more and more attention and preserving the privacy of the pedestrian images used by ReID methods become essential. De-identification (DeID) methods alleviate privacy issues by removing the identity-related of the ReID data. However, most of the existing DeID methods tend to remove all personal identity-related information and compromise the usability of de-identified data on the ReID task. In this paper, we aim to develop a technique that can achieve a good trade-off between privacy protection and data usability for person ReID. To achieve this, we propose a novel de-identification method designed explicitly for person ReID, named Person Identify Shift (PIS). PIS removes the absolute identity in a pedestrian image while preserving the identity relationship between image pairs. By exploiting the interpolation property of variational auto-encoder, PIS shifts each pedestrian image from the current identity to another with a new identity, resulting in images still preserving the relative identities. Experimental results show that our method has a better trade-off between privacy-preserving and model performance than existing de-identification methods and can defend against human and model attacks for data privacy.

Yubin Wang, Zhikang Zou, Xiaoqing Ye et al.

We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains. Due to substantial disparities in data distribution and variations in taxonomy across diverse domains, training such a detector by simply merging datasets poses a significant challenge. Motivated by this observation, we introduce multi-stage prompting modules for multi-dataset 3D detection, which leverages prompts based on the characteristics of corresponding datasets to mitigate existing differences. This elegant design facilitates seamless plug-and-play integration within various advanced 3D detection frameworks in a unified manner, while also allowing straightforward adaptation for universal applicability across datasets. Experiments are conducted across multiple dataset consolidation scenarios involving KITTI, Waymo, and nuScenes, demonstrating that our Uni$^2$Det outperforms existing methods by a large margin in multi-dataset training. Notably, results on zero-shot cross-dataset transfer validate the generalization capability of our proposed method.

Junyao Gao, Yanchen Liu, Yanan Sun et al.

In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a style-aware encoder and a well-organized style dataset called StyleGallery. With dedicated design for style learning, this style-aware encoder is trained to extract expressive style representation with decoupling training strategy, and StyleGallery enables the generalization ability. We further employ a content-fusion encoder to enhance image-driven style transfer. We highlight that, our approach, named StyleShot, is simple yet effective in mimicking various desired styles, i.e., 3D, flat, abstract or even fine-grained styles, without test-time tuning. Rigorous experiments validate that, StyleShot achieves superior performance across a wide range of styles compared to existing state-of-the-art methods. The project page is available at: https://styleshot.github.io/.

Yubin Wang, Xinyang Jiang, De Cheng et al.

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input to enhance prompt effectiveness. Nevertheless, conventional descriptions fall short of structured information that effectively represents the interconnections among entities or attributes linked to a particular category. To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations. Preexisting prompt tuning methods exhibit inadequacies in managing this structured knowledge. Consequently, we propose a novel approach called Hierarchical Prompt Tuning (HPT), which enables simultaneous modeling of both structured and conventional linguistic knowledge. Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning. In addition, by incorporating high-level and global-level prompts modeling overall semantics, the proposed hierarchical structure forges cross-level interlinks and empowers the model to handle more complex and long-term relationships. Extensive experiments demonstrate that our HPT shows strong effectiveness and generalizes much better than existing SOTA methods. Our code is available at https://github.com/Vill-Lab/2024-AAAI-HPT.

Xiaowen Zhang, Zijie Yue, Yong Luo et al.

Object counting is a fundamental task in computer vision, with broad applicability in many real-world scenarios. Fully-supervised counting methods require costly point-level annotations per object. Few weakly-supervised methods leverage only image-level object counts as supervision and achieve fairly promising results. They are, however, often limited to counting a single category, e.g. person. In this paper, we propose WS-COC, the first MLLM-driven weakly-supervised framework for class-agnostic object counting. Instead of directly fine-tuning MLLMs to predict object counts, which can be challenging due to the modality gap, we incorporate three simple yet effective strategies to bootstrap the counting paradigm in both training and testing: First, a divide-and-discern dialogue tuning strategy is proposed to guide the MLLM to determine whether the object count falls within a specific range and progressively break down the range through multi-round dialogue. Second, a compare-and-rank count optimization strategy is introduced to train the MLLM to optimize the relative ranking of multiple images according to their object counts. Third, a global-and-local counting enhancement strategy aggregates and fuses local and global count predictions to improve counting performance in dense scenes. Extensive experiments on FSC-147, CARPK, PUCPR+, and ShanghaiTech show that WS-COC matches or even surpasses many state-of-art fully-supervised methods while significantly reducing annotation costs. Code is available at https://github.com/viscom-tongji/WS-COC.

Zefan Qu, Xinyang Jiang, Yifan Yang et al.

Low latency rates are crucial for online video-based applications, such as video conferencing and cloud gaming, which make improving video quality in online scenarios increasingly important. However, existing quality enhancement methods are limited by slow inference speed and the requirement for temporal information contained in future frames, making it challenging to deploy them directly in online tasks. In this paper, we propose a novel method, STLVQE, specifically designed to address the rarely studied online video quality enhancement (Online-VQE) problem. Our STLVQE designs a new VQE framework which contains a Module-Agnostic Feature Extractor that greatly reduces the redundant computations and redesign the propagation, alignment, and enhancement module of the network. A Spatial-Temporal Look-up Tables (STL) is proposed, which extracts spatial-temporal information in videos while saving substantial inference time. To the best of our knowledge, we are the first to exploit the LUT structure to extract temporal information in video tasks. Extensive experiments on the MFQE 2.0 dataset demonstrate that our STLVQE achieves a satisfactory performance-speed trade-off.

Yubin Wang, Xinyang Jiang, De Cheng et al.

Video temporal grounding is an emerging topic aiming to identify specific clips within videos. In addition to pre-trained video models, contemporary methods utilize pre-trained vision-language models (VLM) to capture detailed characteristics of diverse scenes and objects from video frames. However, as pre-trained on images, VLM may struggle to distinguish action-sensitive patterns from static objects, making it necessary to adapt them to specific data domains for effective feature representation over temporal grounding. We address two primary challenges to achieve this goal. Specifically, to mitigate high adaptation costs, we propose an efficient preliminary in-domain fine-tuning paradigm for feature adaptation, where downstream-adaptive features are learned through several pretext tasks. Furthermore, to integrate action-sensitive information into VLM, we introduce Action-Cue-Injected Temporal Prompt Learning (ActPrompt), which injects action cues into the image encoder of VLM for better discovering action-sensitive patterns. Extensive experiments demonstrate that ActPrompt is an off-the-shelf training framework that can be effectively applied to various SOTA methods, resulting in notable improvements. The complete code used in this study is provided in the supplementary materials.

Yubin Wang, Xinyang Jiang, De Cheng et al.

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using category-related descriptions to enhance prompt effectiveness. However, conventional descriptions lack explicit structured information necessary to represent the interconnections among key elements like entities or attributes with relation to a particular category. Since existing prompt tuning methods give little consideration to managing structured knowledge, this paper advocates leveraging LLMs to construct a graph for each description to prioritize such structured knowledge. Consequently, we propose a novel approach called Hierarchical Prompt Tuning (HPT), enabling simultaneous modeling of both structured and conventional linguistic knowledge. Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning. In addition, by incorporating high-level and global-level prompts modeling overall semantics, the proposed hierarchical structure forges cross-level interlinks and empowers the model to handle more complex and long-term relationships. Finally, by enhancing multi-granularity knowledge generation, redesigning the relationship-driven attention re-weighting module, and incorporating consistent constraints on the hierarchical text encoder, we propose HPT++, which further improves the performance of HPT. Our experiments are conducted across a wide range of evaluation settings, including base-to-new generalization, cross-dataset evaluation, and domain generalization. Extensive results and ablation studies demonstrate the effectiveness of our methods, which consistently outperform existing SOTA methods.

Miaojing Shi, Xiaowen Zhang, Zijie Yue et al.

Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category information in images. This however is insufficient for training the model to accurately distinguish the number of objects in the counting task. To this end, we propose QUANet, which introduces novel quantity-oriented text prompts with a vision-text quantity alignment loss to enhance the model's quantity awareness. Moreover, we propose a dual-stream adaptive counting decoder consisting of a Transformer stream, a CNN stream, and a number of Transformer-to-CNN enhancement adapters (T2C-adapters) for density map prediction. The T2C-adapters facilitate the effective knowledge communication and aggregation between the Transformer and CNN streams. A cross-stream quantity ranking loss is proposed in the end to optimize the ranking orders of predictions from the two streams. Extensive experiments on standard benchmarks such as FSC-147, CARPK, PUCPR+, and ShanghaiTech demonstrate our model's strong generalizability for zero-shot class-agnostic counting. Code is available at https://github.com/viscom-tongji/QUANet

Shuguang Dou, Xiangyang Jiang, Yuanpeng Tu et al.

The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features. ReID focuses on instance part-level differences between pedestrian parts, while human parsing centers on semantic spatial context, reflecting the internal structure of the human body. To address this, DROP decouples features for ReID and human parsing, proposing detail-preserving upsampling to combine varying resolution feature maps. Parsing-specific features for human parsing are decoupled, and human position information is exclusively added to the human parsing branch. In the ReID branch, a part-aware compactness loss is introduced to enhance instance-level part differences. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods. The codebase is accessible at https://github.com/shuguang-52/DROP.

Junyao Gao, Jiaxing Li, Wenran Liu et al.

In this paper, we propose \textbf{CharacterShot}, a controllable and consistent 4D character animation framework that enables any individual designer to create dynamic 3D characters (i.e., 4D character animation) from a single reference character image and a 2D pose sequence. We begin by pretraining a powerful 2D character animation model based on a cutting-edge DiT-based image-to-video model, which allows for any 2D pose sequnce as controllable signal. We then lift the animation model from 2D to 3D through introducing dual-attention module together with camera prior to generate multi-view videos with spatial-temporal and spatial-view consistency. Finally, we employ a novel neighbor-constrained 4D gaussian splatting optimization on these multi-view videos, resulting in continuous and stable 4D character representations. Moreover, to improve character-centric performance, we construct a large-scale dataset Character4D, containing 13,115 unique characters with diverse appearances and motions, rendered from multiple viewpoints. Extensive experiments on our newly constructed benchmark, CharacterBench, demonstrate that our approach outperforms current state-of-the-art methods. Code, models, and datasets will be publicly available at https://github.com/Jeoyal/CharacterShot.

Weicai Ye, Chenhao Ji, Zheng Chen et al.

Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses.

Junyao Gao, Yanan Sun, Fei Shen et al.

In this paper, we present FaceShot, a novel training-free portrait animation framework designed to bring any character into life from any driven video without fine-tuning or retraining. We achieve this by offering precise and robust reposed landmark sequences from an appearance-guided landmark matching module and a coordinate-based landmark retargeting module. Together, these components harness the robust semantic correspondences of latent diffusion models to produce facial motion sequence across a wide range of character types. After that, we input the landmark sequences into a pre-trained landmark-driven animation model to generate animated video. With this powerful generalization capability, FaceShot can significantly extend the application of portrait animation by breaking the limitation of realistic portrait landmark detection for any stylized character and driven video. Also, FaceShot is compatible with any landmark-driven animation model, significantly improving overall performance. Extensive experiments on our newly constructed character benchmark CharacBench confirm that FaceShot consistently surpasses state-of-the-art (SOTA) approaches across any character domain. More results are available at our project website https://faceshot2024.github.io/faceshot/.

Zhenyang Liu, Sixiao Zheng, Siyu Chen et al.

Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language fields through neural representations enables accurate understanding of 3D scenes from limited viewpoints and facilitates the localization of target objects in complex environments. However, existing language field methods struggle to accurately localize instances using spatial relations in language queries, such as ``the book on the chair.'' This limitation mainly arises from inadequate reasoning about spatial relations in both language queries and 3D scenes. In this work, we propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning that constructs a visual properties-enhanced hierarchical feature field for open-vocabulary 3D visual grounding. To enable spatial reasoning in language queries, SpatialReasoner fine-tunes an LLM to capture spatial relations and explicitly infer instructions for the target, anchor, and spatial relation. To enable spatial reasoning in 3D scenes, SpatialReasoner incorporates visual properties (opacity and color) to construct a hierarchical feature field. This field represents language and instance features using distilled CLIP features and masks extracted via the Segment Anything Model (SAM). The field is then queried using the inferred instructions in a hierarchical manner to localize the target 3D instance based on the spatial relation in the language query. Extensive experiments show that our framework can be seamlessly integrated into different neural representations, outperforming baseline models in 3D visual grounding while empowering their spatial reasoning capability.

Junyao Gao, Sibo Liu, Jiaxing Li et al.

In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We achieve this by leveraging the consistent text-to-image style mapping capability of current large generative models, which can generate images in the same style from a given style description. Building on this foundation, we curate a diverse and balanced prompt gallery with 170K style prompts and 400K content prompts, and generate a large-scale style dataset MegaStyle-1.4M via content-style prompt combinations. With MegaStyle-1.4M, we propose style-supervised contrastive learning to fine-tune a style encoder MegaStyle-Encoder for extracting expressive, style-specific representations, and we also train a FLUX-based style transfer model MegaStyle-FLUX. Extensive experiments demonstrate the importance of maintaining intra-style consistency, inter-style diversity and high-quality for style dataset, as well as the effectiveness of the proposed MegaStyle-1.4M. Moreover, when trained on MegaStyle-1.4M, MegaStyle-Encoder and MegaStyle-FLUX provide reliable style similarity measurement and generalizable style transfer, making a significant contribution to the style transfer community. More results are available at our project website https://jeoyal.github.io/MegaStyle/.

Yubin Wang, Xinyang Jiang, De Cheng et al.

Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for enhancing AI reliability and enabling AI-driven knowledge discovery. In this paper, rather than learning abstract prompt embeddings, we propose the first framework, named Interpretable Visual Prompt Tuning (IVPT), to explore interpretability for visual prompts, by introducing hierarchical concept prototypes. Specifically, visual prompts are linked to human-understandable semantic concepts, represented as a set of category-agnostic prototypes, each corresponding to a specific region of the image. Then, IVPT aggregates features from these regions to generate interpretable prompts, which are structured hierarchically to explain visual prompts at different granularities. Comprehensive qualitative and quantitative evaluations on fine-grained classification benchmarks show its superior interpretability and performance over conventional visual prompt tuning methods and existing interpretable methods.

Zifan Song, Kaitao Song, Guosheng Hu et al.

Recent advancements in large language models (LLMs) and agentic systems have shown exceptional decision-making capabilities, revealing significant potential for autonomic finance. Current financial trading agents predominantly simulate anthropomorphic roles that inadvertently introduce emotional biases and rely on peripheral information, while being constrained by the necessity for continuous inference during deployment. In this paper, we pioneer the harmonization of strategic depth in agents with the mechanical rationality essential for quantitative trading. Consequently, we present TiMi (Trade in Minutes), a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment. TiMi leverages specialized LLM capabilities of semantic analysis, code programming, and mathematical reasoning within a comprehensive policy-optimization-deployment chain. Specifically, we propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection. Extensive evaluations across 200+ trading pairs in stock and cryptocurrency markets empirically validate the efficacy of TiMi in stable profitability, action efficiency, and risk control under volatile market dynamics.

Chenhao Ji, Chaohui Yu, Junyao Gao et al.

Recently, camera-controlled video generation has seen rapid development, offering more precise control over video generation. However, existing methods predominantly focus on camera control in perspective projection video generation, while geometrically consistent panoramic video generation remains challenging. This limitation is primarily due to the inherent complexities in panoramic pose representation and spherical projection. To address this issue, we propose CamPVG, the first diffusion-based framework for panoramic video generation guided by precise camera poses. We achieve camera position encoding for panoramic images and cross-view feature aggregation based on spherical projection. Specifically, we propose a panoramic Plücker embedding that encodes camera extrinsic parameters through spherical coordinate transformation. This pose encoder effectively captures panoramic geometry, overcoming the limitations of traditional methods when applied to equirectangular projections. Additionally, we introduce a spherical epipolar module that enforces geometric constraints through adaptive attention masking along epipolar lines. This module enables fine-grained cross-view feature aggregation, substantially enhancing the quality and consistency of generated panoramic videos. Extensive experiments demonstrate that our method generates high-quality panoramic videos consistent with camera trajectories, far surpassing existing methods in panoramic video generation.

Chuang-Wei Liu, Mingjian Sun, Cairong Zhao et al.

Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations. Typical unsupervised methods rely on the multi-view consistency assumption for training networks, which suffer considerably from stereo matching ambiguities, such as repetitive patterns and texture-less regions. A feasible solution lies in transferring 3D geometric knowledge from a relative depth map to the stereo matching networks. However, existing knowledge transfer methods learn depth ranking information from randomly built sparse correspondences, which makes inefficient utilization of 3D geometric knowledge and introduces noise from mistaken disparity estimates. This work proposes a novel unsupervised learning framework to address these challenges, which comprises a plug-and-play disparity confidence estimation algorithm and two depth prior-guided loss functions. Specifically, the local coherence consistency between neighboring disparities and their corresponding relative depths is first checked to obtain disparity confidence. Afterwards, quasi-dense correspondences are built using only confident disparity estimates to facilitate efficient depth ranking learning. Finally, a dual disparity smoothness loss is proposed to boost stereo matching performance at disparity discontinuities. Experimental results demonstrate that our method achieves state-of-the-art stereo matching accuracy on the KITTI Stereo benchmarks among all unsupervised stereo matching methods.

Yutong Liu, Cairong Zhao, Guosheng Hu

For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often evaluated under different settings because a method typically contains multiple components. Analyzing connections among existing methods is important for deeper understanding. To bridge these gaps, we conduct an extensive review of state-of-the-art methods and perform comprehensive evaluations under the same conditions for fair comparison. To our knowledge, such a fair and extensive investigation remains critically underexplored. To better understand connections, first, we decouple published quantization methods into two steps: pre-quantization transformation and quantization error mitigation. The former is a preprocessing step that reduces outlier impact by flattening the data distribution; the latter offsets quantization errors to improve performance. Second, we evaluate and analyze the impact of different settings, including granularity and symmetry. Third, we analyze and evaluate the latest MXFP4 and NVFP4 data formats and their performance. Our experiments first demonstrate that optimized rotation and scaling yield the best pre-quantization performance, and that combining low-rank compensation with GPTQ can occasionally outperform GPTQ alone for error mitigation. Second, finer granularity improves performance but increases storage overhead. Third, we find that scaling-factor format and precision greatly affect FP4 performance, and that rotation-based strategies effective for INT4 offer limited gains for MXFP4 and NVFP4, motivating further study.

Cairong Zhao, Yufeng Jin, Zifan Song et al.

Deep learning achieved great progress recently, however, it is not easy or efficient to further improve its performance by increasing the size of the model. Multi-modal learning can mitigate this challenge by introducing richer and more discriminative information as input. To solve the problem of limited access to multi-modal data at the time of use, we conduct multi-modal learning by introducing a teacher model to transfer discriminative knowledge to a student model during training. However, this knowledge transfer via distillation is not trivial because the big domain gap between the widely differing modalities can easily lead to overfitting. In this work, we introduce a cross-modal distillation framework. Specifically, we find hard constrained loss, e.g. l2 loss forcing the student being exact the same as the teacher, can easily lead to overfitting in cross-modality distillation. To address this, we propose two soft constrained knowledge distillation strategies at the feature level and classifier level respectively. In addition, we propose a quality-based adaptive weights module to weigh input samples via quantified data quality, leading to robust model training. We conducted experiments on speaker recognition and image classification tasks, and the results show that our approach is able to effectively achieve knowledge transfer between the commonly used and widely differing modalities of image, text, and speech.

Jiale Zhao, Xinyang Jiang, Junyao Gao et al.

Unified vision-language models(VLMs) have recently shown remarkable progress, enabling a single model to flexibly address diverse tasks through different instructions within a shared computational architecture. This instruction-based control mechanism creates unique security challenges, as adversarial inputs must remain effective across multiple task instructions that may be unpredictably applied to process the same malicious content. In this paper, we introduce CrossVLAD, a new benchmark dataset carefully curated from MSCOCO with GPT-4-assisted annotations for systematically evaluating cross-task adversarial attacks on unified VLMs. CrossVLAD centers on the object-change objective-consistently manipulating a target object's classification across four downstream tasks-and proposes a novel success rate metric that measures simultaneous misclassification across all tasks, providing a rigorous evaluation of adversarial transferability. To tackle this challenge, we present CRAFT (Cross-task Region-based Attack Framework with Token-alignment), an efficient region-centric attack method. Extensive experiments on Florence-2 and other popular unified VLMs demonstrate that our method outperforms existing approaches in both overall cross-task attack performance and targeted object-change success rates, highlighting its effectiveness in adversarially influencing unified VLMs across diverse tasks.

Le Xu, Qi Zhang, Qixian Zhang et al.

Recent advances in brain-vision decoding have driven significant progress, reconstructing with high fidelity perceived visual stimuli from neural activity, e.g., functional magnetic resonance imaging (fMRI), in the human visual cortex. Most existing methods decode the brain signal using a two-level strategy, i.e., pixel-level and semantic-level. However, these methods rely heavily on low-level pixel alignment yet lack sufficient and fine-grained semantic alignment, resulting in obvious reconstruction distortions of multiple semantic objects. To better understand the brain's visual perception patterns and how current decoding models process semantic objects, we have developed an experimental framework that uses fMRI representations as intervention conditions. By injecting these representations into multi-scale image features via cross-attention, we compare both downstream performance and intermediate feature changes on object detection and instance segmentation tasks with and without fMRI information. Our results demonstrate that incorporating fMRI signals enhances the accuracy of downstream detection and segmentation, confirming that fMRI contains rich multi-object semantic cues and coarse spatial localization information-elements that current models have yet to fully exploit or integrate.

Qilin Shu, Qixian Zhang, Qi Zhang et al.

The person search task aims to locate a target person within a set of scene images. In recent years, transformer-based models in this field have made some progress. However, they still face three primary challenges: 1) the self-attention mechanism tends to suppress high-frequency components in the features, which severely impacts model performance; 2) the computational cost of transformers is relatively high. To address these issues, we propose a novel High-frequency Augmentation and Multi-Wave mixing (HAMW) method for person search. HAMW is designed to enhance the discriminative feature extraction capabilities of transformers while reducing computational overhead and improving efficiency. Specifically, we develop a three-stage framework that progressively optimizes both detection and re-identification performance. Our model enhances the perception of high-frequency features by learning from augmented inputs containing additional high-frequency components. Furthermore, we replace the self-attention layers in the transformer with a strategy based on multi-level Haar wavelet fusion to capture multi-scale features. This not only lowers the computational complexity but also alleviates the suppression of high-frequency features and enhances the ability to exploit multi-scale information. Extensive experiments demonstrate that HAMW achieves state-of-the-art performance on both the CUHK-SYSU and PRW datasets.

Ruihao Xi, Xuekuan Wang, Yongcheng Li et al.

Generating realistic and controllable human motions, particularly those involving rich multi-character interactions, remains a significant challenge due to data scarcity and the complexities of modeling inter-personal dynamics. To address these limitations, we first introduce a new large-scale rich video human motion 2D dataset (Motion2D-Video-150K) comprising 150,000 video sequences. Motion2D-Video-150K features a balanced distribution of diverse single-character and, crucially, double-character interactive actions, each paired with detailed textual descriptions. Building upon this dataset, we propose a novel diffusion-based rich video human motion2D generation (RVHM2D) model. RVHM2D incorporates an enhanced textual conditioning mechanism utilizing either dual text encoders (CLIP-L/B) or T5-XXL with both global and local features. We devise a two-stage training strategy: the model is first trained with a standard diffusion objective, and then fine-tuned using reinforcement learning with an FID-based reward to further enhance motion realism and text alignment. Extensive experiments demonstrate that RVHM2D achieves leading performance on the Motion2D-Video-150K benchmark in generating both single and interactive double-character scenarios.

Yanting Gao, Yepeng Liu, Junming Liu et al.

Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak transferability in black-box settings due to overfitting. Existing methods improve transferability by diversifying perturbation inputs or applying uniform gradient regularization within surrogate models, yet they have not fully leveraged the shared and unique features of surrogate models trained on the same task, leading to suboptimal transfer performance. Therefore, enhancing perturbations of common information shared by surrogate models and suppressing those tied to individual characteristics offers an effective way to improve transferability. Accordingly, we propose a commonality-oriented gradient optimization strategy (COGO) consisting of two components: Commonality Enhancement (CE) and Individuality Suppression (IS). CE perturbs the mid-to-low frequency regions, leveraging the fact that ViTs trained on the same dataset tend to rely more on mid-to-low frequency information for classification. IS employs adaptive thresholds to evaluate the correlation between backpropagated gradients and model individuality, assigning weights to gradients accordingly. Extensive experiments demonstrate that COGO significantly improves the transfer success rates of adversarial attacks, outperforming current state-of-the-art methods.

Yuhao Xue, Zhifei Zhang, Xinyang Jiang et al.

Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited due to distribution mismatches between generated adversarial features and real-world data. While recent works utilize pre-trained diffusion models as adversarial priors, they still encounter challenges due to the distribution shift between the distribution of ideal adversarial samples and the natural image distribution learned by the diffusion model. To address the challenge, we propose Transferable Robust Adversarial Images via Latent Diffusion (TRAIL), a test-time adaptation framework that enables the model to generate images from a distribution of images with adversarial features and closely resembles the target images. To mitigate the distribution shift, during attacks, TRAIL updates the diffusion U-Net's weights by combining adversarial objectives (to mislead victim models) and perceptual constraints (to preserve image realism). The adapted model then generates adversarial samples through iterative noise injection and denoising guided by these objectives. Experiments demonstrate that TRAIL significantly outperforms state-of-the-art methods in cross-model attack transferability, validating that distribution-aligned adversarial feature synthesis is critical for practical black-box attacks.

Qingsong Zhao, Yi Wang, Zhipeng Zhou et al.

Sequence ordering of word vector matters a lot to text reading, which has been proven in natural language processing (NLP). However, the rule of different sequence ordering in computer vision (CV) was not well explored, e.g., why the ``zigzag" flattening (ZF) is commonly utilized as a default option to get the image patches ordering in vision networks. Notably, when decomposing multi-scale images, the ZF could not maintain the invariance of feature point positions. To this end, we investigate the Hilbert fractal flattening (HF) as another method for sequence ordering in CV and contrast it against ZF. The HF has proven to be superior to other curves in maintaining spatial locality, when performing multi-scale transformations of dimensional space. And it can be easily plugged into most deep neural networks (DNNs). Extensive experiments demonstrate that it can yield consistent and significant performance boosts for a variety of architectures. Finally, we hope that our studies spark further research about the flattening strategy of image reading.