Xun Yang

Xiangchen Yin, Donglin Di, Lei Fan et al.

Recent methods using diffusion models have made significant progress in human image generation with various control signals such as pose priors. However, existing efforts are still struggling to generate high-quality images with consistent pose alignment, resulting in unsatisfactory output. In this paper, we propose a framework that delves into the graph relations of pose priors to provide control information for human image generation. The main idea is to establish a graph topological structure between the pose priors and latent representation of diffusion models to capture the intrinsic associations between different pose parts. A Progressive Graph Integrator (PGI) is designed to learn the spatial relationships of the pose priors with the graph structure, adopting a hierarchical strategy within an Adapter to gradually propagate information across different pose parts. Besides, a pose perception loss is introduced based on a pretrained pose estimation network to minimize the pose differences. Extensive qualitative and quantitative experiments conducted on the Human-Art and LAION-Human datasets clearly demonstrate that our model can achieve significant performance improvement over the latest benchmark models. The code is available at \url{https://xiangchenyin.github.io/GRPose/}.

Sheng Zhou, Dan Guo, Jia Li et al.

Text-based visual question answering (TextVQA) faces the significant challenge of avoiding redundant relational inference. To be specific, a large number of detected objects and optical character recognition (OCR) tokens result in rich visual relationships. Existing works take all visual relationships into account for answer prediction. However, there are three observations: (1) a single subject in the images can be easily detected as multiple objects with distinct bounding boxes (considered repetitive objects). The associations between these repetitive objects are superfluous for answer reasoning; (2) two spatially distant OCR tokens detected in the image frequently have weak semantic dependencies for answer reasoning; and (3) the co-existence of nearby objects and tokens may be indicative of important visual cues for predicting answers. Rather than utilizing all of them for answer prediction, we make an effort to identify the most important connections or eliminate redundant ones. We propose a sparse spatial graph network (SSGN) that introduces a spatially aware relation pruning technique to this task. As spatial factors for relation measurement, we employ spatial distance, geometric dimension, overlap area, and DIoU for spatially aware pruning. We consider three visual relationships for graph learning: object-object, OCR-OCR tokens, and object-OCR token relationships. SSGN is a progressive graph learning architecture that verifies the pivotal relations in the correlated object-token sparse graph, and then in the respective object-based sparse graph and token-based sparse graph. Experiment results on TextVQA and ST-VQA datasets demonstrate that SSGN achieves promising performances. And some visualization results further demonstrate the interpretability of our method.

Shanshan Wang, ALuSi, Xun Yang et al.

Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity of training samples is an effective solution. However, existing augmentation approaches always have some limitations. On the one hand, the augmentation manner in most DG methods is not enough as the model may not see the perturbed features in approximate the worst case due to the randomness, thus the transferability in features could not be fully explored. On the other hand, the causality in discriminative features is not involved in these methods, which harms the generalization ability of model due to the spurious correlations. To address these issues, we propose a Dual-stream Feature Augmentation~(DFA) method by constructing some hard features from two perspectives. Firstly, to improve the transferability, we construct some targeted features with domain related augmentation manner. Through the guidance of uncertainty, some hard cross-domain fictitious features are generated to simulate domain shift. Secondly, to take the causality into consideration, the spurious correlated non-causal information is disentangled by an adversarial mask, then the more discriminative features can be extracted through these hard causal related information. Different from previous fixed synthesizing strategy, the two augmentations are integrated into a unified learnable feature disentangle model. Based on these hard features, contrastive learning is employed to keep the semantic consistency and improve the robustness of the model. Extensive experiments on several datasets demonstrated that our approach could achieve state-of-the-art performance for domain generalization. Our code is available at: https://github.com/alusi123/DFA.

Sheng Zhou, Junbin Xiao, Xun Yang et al.

Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scenetext recognition and promoting research towards interpretable QA. The task has three-fold significance. First, it encourages scene-text evidence versus other short-cuts for answer predictions. Second, it directly accepts scene-text regions as visual answers, thus circumventing the problem of ineffective answer evaluation by stringent string matching. Third, it isolates the challenges inherited in VideoQA and scene-text recognition. This enables the diagnosis of the root causes for failure predictions, e.g., wrong QA or wrong scene-text recognition? To achieve Grounded TextVideoQA, we propose the T2S-QA model that highlights a disentangled temporal-to-spatial contrastive learning strategy for weakly-supervised scene-text grounding and grounded TextVideoQA. To facilitate evaluation, we construct a new dataset ViTXT-GQA which features 52K scene-text bounding boxes within 2.2K temporal segments related to 2K questions and 729 videos. With ViTXT-GQA, we perform extensive experiments and demonstrate the severe limitations of existing techniques in Grounded TextVideoQA. While T2S-QA achieves superior results, the large performance gap with human leaves ample space for improvement. Our further analysis of oracle scene-text inputs posits that the major challenge is scene-text recognition. To advance the research of Grounded TextVideoQA, our dataset and code are at https://github.com/zhousheng97/ViTXT-GQA.git

Yicong Li, Xun Yang, An Zhang et al.

This paper identifies two kinds of redundancy in the current VideoQA paradigm. Specifically, the current video encoders tend to holistically embed all video clues at different granularities in a hierarchical manner, which inevitably introduces \textit{neighboring-frame redundancy} that can overwhelm detailed visual clues at the object level. Subsequently, prevailing vision-language fusion designs introduce the \textit{cross-modal redundancy} by exhaustively fusing all visual elements with question tokens without explicitly differentiating their pairwise vision-language interactions, thus making a pernicious impact on the answering. To this end, we propose a novel transformer-based architecture, that aims to model VideoQA in a redundancy-aware manner. To address the neighboring-frame redundancy, we introduce a video encoder structure that emphasizes the object-level change in neighboring frames, while adopting an out-of-neighboring message-passing scheme that imposes attention only on distant frames. As for the cross-modal redundancy, we equip our fusion module with a novel adaptive sampling, which explicitly differentiates the vision-language interactions by identifying a small subset of visual elements that exclusively support the answer. Upon these advancements, we find this \underline{R}edundancy-\underline{a}ware trans\underline{former} (RaFormer) can achieve state-of-the-art results on multiple VideoQA benchmarks.

Ning Han, Xun Yang, Ee-Peng Lim et al.

Cross-modal video retrieval aims to retrieve the semantically relevant videos given a text as a query, and is one of the fundamental tasks in Multimedia. Most of top-performing methods primarily leverage Visual Transformer (ViT) to extract video features [1, 2, 3], suffering from high computational complexity of ViT especially for encoding long videos. A common and simple solution is to uniformly sample a small number (say, 4 or 8) of frames from the video (instead of using the whole video) as input to ViT. The number of frames has a strong influence on the performance of ViT, e.g., using 8 frames performs better than using 4 frames yet needs more computational resources, resulting in a trade-off. To get free from this trade-off, this paper introduces an automatic video compression method based on a bilevel optimization program (BOP) consisting of both model-level (i.e., base-level) and frame-level (i.e., meta-level) optimizations. The model-level learns a cross-modal video retrieval model whose input is the "compressed frames" learned by frame-level optimization. In turn, the frame-level optimization is through gradient descent using the meta loss of video retrieval model computed on the whole video. We call this BOP method as well as the "compressed frames" as Meta-Optimized Frames (MOF). By incorporating MOF, the video retrieval model is able to utilize the information of whole videos (for training) while taking only a small number of input frames in actual implementation. The convergence of MOF is guaranteed by meta gradient descent algorithms. For evaluation, we conduct extensive experiments of cross-modal video retrieval on three large-scale benchmarks: MSR-VTT, MSVD, and DiDeMo. Our results show that MOF is a generic and efficient method to boost multiple baseline methods, and can achieve a new state-of-the-art performance.

Shengkai Sun, Daizong Liu, Jianfeng Dong et al.

Unsupervised pre-training has shown great success in skeleton-based action understanding recently. Existing works typically train separate modality-specific models, then integrate the multi-modal information for action understanding by a late-fusion strategy. Although these approaches have achieved significant performance, they suffer from the complex yet redundant multi-stream model designs, each of which is also limited to the fixed input skeleton modality. To alleviate these issues, in this paper, we propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL, which exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner. Specifically, instead of designing separate modality-specific optimization processes for uni-modal unsupervised learning, we feed different modality inputs into the same stream with an early-fusion strategy to learn their multi-modal features for reducing model complexity. To ensure that the fused multi-modal features do not exhibit modality bias, i.e., being dominated by a certain modality input, we further propose both intra- and inter-modal consistency learning to guarantee that the multi-modal features contain the complete semantics of each modal via feature decomposition and distinct alignment. In this manner, our framework is able to learn the unified representations of uni-modal or multi-modal skeleton input, which is flexible to different kinds of modality input for robust action understanding in practical cases. Extensive experiments conducted on three large-scale datasets, i.e., NTU-60, NTU-120, and PKU-MMD II, demonstrate that UmURL is highly efficient, possessing the approximate complexity with the uni-modal methods, while achieving new state-of-the-art performance across various downstream task scenarios in skeleton-based action representation learning.

Haowen Pan, Yixin Cao, Xiaozhi Wang et al.

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry. In this paper, we propose a novel method to identify key neurons for interpretability -- how multi-modal LLMs bridge visual and textual concepts for captioning. Our method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation. Based on those identified neurons, we further design a multi-modal knowledge editing method, beneficial to mitigate sensitive words or hallucination. For rationale of our design, we provide theoretical assumption. For empirical evaluation, we have conducted extensive quantitative and qualitative experiments. The results not only validate the effectiveness of our methods, but also offer insightful findings that highlight three key properties of multi-modal neurons: sensitivity, specificity and causal-effect, to shed light for future research.

Muyang Li, Runze Wu, Haoyu Liu et al.

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning pseudo-labels to confident unlabeled instances and incorporating them into the training set. Therefore, the selection criteria of confident instances are crucial to the success of SSL. Recently, there has been growing interest in the development of SSL methods that use dynamic or adaptive thresholds. Yet, these methods typically apply the same threshold to all samples, or use class-dependent thresholds for instances belonging to a certain class, while neglecting instance-level information. In this paper, we propose the study of instance-dependent thresholds, which has the highest degree of freedom compared with existing methods. Specifically, we devise a novel instance-dependent threshold function for all unlabeled instances by utilizing their instance-level ambiguity and the instance-dependent error rates of pseudo-labels, so instances that are more likely to have incorrect pseudo-labels will have higher thresholds. Furthermore, we demonstrate that our instance-dependent threshold function provides a bounded probabilistic guarantee for the correctness of the pseudo-labels it assigns.

Shanshan Wang, Zhen Zeng, Xun Yang et al.

Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specific knowledge concepts. Despite the effectiveness of existing efforts, previous methods always considered the mastery level on the whole students, so they still suffer from the Long Tail Effect. A large number of students who have sparse data are performed poorly in the model. To relieve the situation, we proposed a Self-supervised Cognitive Diagnosis (SCD) framework which leverages the self-supervised manner to assist the graph-based cognitive diagnosis, then the performance on those students with sparse data can be improved. Specifically, we came up with a graph confusion method that drops edges under some special rules to generate different sparse views of the graph. By maximizing the consistency of the representation on the same node under different views, the model could be more focused on long-tailed students. Additionally, we proposed an importance-based view generation rule to improve the influence of long-tailed students. Extensive experiments on real-world datasets show the effectiveness of our approach, especially on the students with sparse data.

Fangming Cui, Xun Yang, Chao Wu et al.

Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization performance due to the invalidity of the learned text embeddings for unseen tasks. A straightforward approach to bridge this gap is to freeze the text embeddings in prompts, which results in a lack of capacity to adapt VLMs for downstream tasks. To address this dilemma, we propose a paradigm called EnPrompt with a novel External Layer (EnLa). Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks. The learnable external layer is built upon valid embeddings of pre-trained CLIP. This design considers the balance of learning capabilities between the two branches. To align the textual and visual features, we propose a novel two-pronged approach: i) we introduce the optimal transport as the discrepancy metric to align the vision and text modalities, and ii) we introduce a novel strengthening feature to enhance the interaction between these two modalities. Four representative experiments (i.e., base-to-novel generalization, few-shot learning, cross-dataset generalization, domain shifts generalization) across 15 datasets demonstrate that our method outperforms the existing prompt learning method.

Sheng Zhou, Junbin Xiao, Qingyun Li et al.

We introduce EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text. EgoTextVQA contains 1.5K ego-view videos and 7K scene-text aware questions that reflect real user needs in outdoor driving and indoor house-keeping activities. The questions are designed to elicit identification and reasoning on scene text in an egocentric and dynamic environment. With EgoTextVQA, we comprehensively evaluate 10 prominent multimodal large language models. Currently, all models struggle, and the best results (Gemini 1.5 Pro) are around 33\% accuracy, highlighting the severe deficiency of these techniques in egocentric QA assistance. Our further investigations suggest that precise temporal grounding and multi-frame reasoning, along with high resolution and auxiliary scene-text inputs, are key for better performance. With thorough analyses and heuristic suggestions, we hope EgoTextVQA can serve as a solid testbed for research in egocentric scene-text QA assistance. Our dataset is released at: https://github.com/zhousheng97/EgoTextVQA.

Yanlong Xu, Haoxuan Qu, Jun Liu et al.

The goal of point cloud localization based on linguistic description is to identify a 3D position using textual description in large urban environments, which has potential applications in various fields, such as determining the location for vehicle pickup or goods delivery. Ideally, for a textual description and its corresponding 3D location, the objects around the 3D location should be fully described in the text description. However, in practical scenarios, e.g., vehicle pickup, passengers usually describe only the part of the most significant and nearby surroundings instead of the entire environment. In response to this $\textbf{partially relevant}$ challenge, we propose $\textbf{CMMLoc}$, an uncertainty-aware $\textbf{C}$auchy-$\textbf{M}$ixture-$\textbf{M}$odel ($\textbf{CMM}$) based framework for text-to-point-cloud $\textbf{Loc}$alization. To model the uncertain semantic relations between text and point cloud, we integrate CMM constraints as a prior during the interaction between the two modalities. We further design a spatial consolidation scheme to enable adaptive aggregation of different 3D objects with varying receptive fields. To achieve precise localization, we propose a cardinal direction integration module alongside a modality pre-alignment strategy, helping capture the spatial relationships among objects and bringing the 3D objects closer to the text modality. Comprehensive experiments validate that CMMLoc outperforms existing methods, achieving state-of-the-art results on the KITTI360Pose dataset. Codes are available in this GitHub repository https://github.com/kevin301342/CMMLoc.

Donglin Di, Jiahui Yang, Chaofan Luo et al.

Text-to-3D generation represents an exciting field that has seen rapid advancements, facilitating the transformation of textual descriptions into detailed 3D models. However, current progress often neglects the intricate high-order correlation of geometry and texture within 3D objects, leading to challenges such as over-smoothness, over-saturation and the Janus problem. In this work, we propose a method named ``3D Gaussian Generation via Hypergraph (Hyper-3DG)'', designed to capture the sophisticated high-order correlations present within 3D objects. Our framework is anchored by a well-established mainflow and an essential module, named ``Geometry and Texture Hypergraph Refiner (HGRefiner)''. This module not only refines the representation of 3D Gaussians but also accelerates the update process of these 3D Gaussians by conducting the Patch-3DGS Hypergraph Learning on both explicit attributes and latent visual features. Our framework allows for the production of finely generated 3D objects within a cohesive optimization, effectively circumventing degradation. Extensive experimentation has shown that our proposed method significantly enhances the quality of 3D generation while incurring no additional computational overhead for the underlying framework. (Project code: https://github.com/yjhboy/Hyper3DG)

Jianfeng Dong, Xiaoman Peng, Zhe Ma et al.

Attribute-specific fashion retrieval (ASFR) is a challenging information retrieval task, which has attracted increasing attention in recent years. Different from traditional fashion retrieval which mainly focuses on optimizing holistic similarity, the ASFR task concentrates on attribute-specific similarity, resulting in more fine-grained and interpretable retrieval results. As the attribute-specific similarity typically corresponds to the specific subtle regions of images, we propose a Region-to-Patch Framework (RPF) that consists of a region-aware branch and a patch-aware branch to extract fine-grained attribute-related visual features for precise retrieval in a coarse-to-fine manner. In particular, the region-aware branch is first to be utilized to locate the potential regions related to the semantic of the given attribute. Then, considering that the located region is coarse and still contains the background visual contents, the patch-aware branch is proposed to capture patch-wise attribute-related details from the previous amplified region. Such a hybrid architecture strikes a proper balance between region localization and feature extraction. Besides, different from previous works that solely focus on discriminating the attribute-relevant foreground visual features, we argue that the attribute-irrelevant background features are also crucial for distinguishing the detailed visual contexts in a contrastive manner. Therefore, a novel E-InfoNCE loss based on the foreground and background representations is further proposed to improve the discrimination of attribute-specific representation. Extensive experiments on three datasets demonstrate the effectiveness of our proposed framework, and also show a decent generalization of our RPF on out-of-domain fashion images. Our source code is available at https://github.com/HuiGuanLab/RPF.

Xun Yang, Fuli Feng, Wei Ji et al.

We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. Despite their effectiveness, current models mostly exploit dataset biases while ignoring the video content, thus leading to poor generalizability. We argue that the issue is caused by the hidden confounder in VMR, {i.e., temporal location of moments}, that spuriously correlates the model input and prediction. How to design robust matching models against the temporal location biases is crucial but, as far as we know, has not been studied yet for VMR. To fill the research gap, we propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction. Specifically, we develop a Deconfounded Cross-modal Matching (DCM) method to remove the confounding effects of moment location. It first disentangles moment representation to infer the core feature of visual content, and then applies causal intervention on the disentangled multimodal input based on backdoor adjustment, which forces the model to fairly incorporate each possible location of the target into consideration. Extensive experiments clearly show that our approach can achieve significant improvement over the state-of-the-art methods in terms of both accuracy and generalization (Codes: \color{blue}{\url{https://github.com/Xun-Yang/Causal_Video_Moment_Retrieval}}

Jianfeng Dong, Zhe Ma, Xiaofeng Mao et al.

This paper strives to predict fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute between fashion items. For example, whether the collar designs of the two clothes are similar. It has potential value in many fashion related applications, such as fashion copyright protection. To this end, we propose an Attribute-Specific Embedding Network (ASEN) to jointly learn multiple attribute-specific embeddings, thus measure the fine-grained similarity in the corresponding space. The proposed ASEN is comprised of a global branch and a local branch. The global branch takes the whole image as input to extract features from a global perspective, while the local branch takes as input the zoomed-in region-of-interest (RoI) w.r.t. the specified attribute thus able to extract more fine-grained features. As the global branch and the local branch extract the features from different perspectives, they are complementary to each other. Additionally, in each branch, two attention modules, i.e., Attribute-aware Spatial Attention and Attribute-aware Channel Attention, are integrated to make ASEN be able to locate the related regions and capture the essential patterns under the guidance of the specified attribute, thus make the learned attribute-specific embeddings better reflect the fine-grained similarity. Extensive experiments on three fashion-related datasets, i.e., FashionAI, DARN, and DeepFashion, show the effectiveness of ASEN for fine-grained fashion similarity prediction and its potential for fashion reranking. Code and data are available at https://github.com/maryeon/asenpp .

Junbin Xiao, Xindi Shang, Xun Yang et al.

In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive visual facts for other high-level video-language tasks (e.g., video-language grounding and video question answering). The challenges in this task include but not limited to: (1) both the subject and object are required to be spatio-temporally localized to ground a query relation; (2) the temporal dynamic nature of visual relations in videos is difficult to capture; and (3) the grounding should be achieved without any direct supervision in space and time. To ground the relations, we tackle the challenges by collaboratively optimizing two sequences of regions over a constructed hierarchical spatio-temporal region graph through relation attending and reconstruction, in which we further propose a message passing mechanism by spatial attention shifting between visual entities. Experimental results demonstrate that our model can not only outperform baseline approaches significantly, but also produces visually meaningful facts to support visual grounding. (Code is available at https://github.com/doc-doc/vRGV).

Kun Li, Xinge Peng, Dan Guo et al.

Repetitive Action Counting (RAC) aims to count the number of repetitive actions occurring in videos. In the real world, repetitive actions have great diversity and bring numerous challenges (e.g., viewpoint changes, non-uniform periods, and action interruptions). Existing methods based on the temporal self-similarity matrix (TSSM) for RAC are trapped in the bottleneck of insufficient capturing action periods when applied to complicated daily videos. To tackle this issue, we propose a novel method named Hybrid Temporal Relation Modeling Network (HTRM-Net) to build diverse TSSM for RAC. The HTRM-Net mainly consists of three key components: bi-modal temporal self-similarity matrix modeling, random matrix dropping, and local temporal context modeling. Specifically, we construct temporal self-similarity matrices by bi-modal (self-attention and dual-softmax) operations, yielding diverse matrix representations from the combination of row-wise and column-wise correlations. To further enhance matrix representations, we propose incorporating a random matrix dropping module to guide channel-wise learning of the matrix explicitly. After that, we inject the local temporal context of video frames and the learned matrix into temporal correlation modeling, which can make the model robust enough to cope with error-prone situations, such as action interruption. Finally, a multi-scale matrix fusion module is designed to aggregate temporal correlations adaptively in multi-scale matrices. Extensive experiments across intra- and cross-datasets demonstrate that the proposed method not only outperforms current state-of-the-art methods but also exhibits robust capabilities in accurately counting repetitive actions in unseen action categories. Notably, our method surpasses the classical TransRAC method by 20.04\% in MAE and 22.76\% in OBO.

Peipei Song, Long Zhang, Long Lan et al.

Partially relevant video retrieval (PRVR) is a practical yet challenging task in text-to-video retrieval, where videos are untrimmed and contain much background content. The pursuit here is of both effective and efficient solutions to capture the partial correspondence between text queries and untrimmed videos. Existing PRVR methods, which typically focus on modeling multi-scale clip representations, however, suffer from content independence and information redundancy, impairing retrieval performance. To overcome these limitations, we propose a simple yet effective approach with active moment discovering (AMDNet). We are committed to discovering video moments that are semantically consistent with their queries. By using learnable span anchors to capture distinct moments and applying masked multi-moment attention to emphasize salient moments while suppressing redundant backgrounds, we achieve more compact and informative video representations. To further enhance moment modeling, we introduce a moment diversity loss to encourage different moments of distinct regions and a moment relevance loss to promote semantically query-relevant moments, which cooperate with a partially relevant retrieval loss for end-to-end optimization. Extensive experiments on two large-scale video datasets (\ie, TVR and ActivityNet Captions) demonstrate the superiority and efficiency of our AMDNet. In particular, AMDNet is about 15.5 times smaller (\#parameters) while 6.0 points higher (SumR) than the up-to-date method GMMFormer on TVR.

Yongjia Ma, Junlin Chen, Donglin Di et al.

Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands. We propose GLC-Diffusion, a tuning-free method for long video generation. It models the long video denoising process by establishing denoising trajectories through Global-Local Collaborative Denoising to ensure overall content consistency and temporal coherence between frames. Additionally, we introduce a Noise Reinitialization strategy which combines local noise shuffling with frequency fusion to improve global content consistency and visual diversity. Further, we propose a Video Motion Consistency Refinement (VMCR) module that computes the gradient of pixel-wise and frequency-wise losses to enhance visual consistency and temporal smoothness. Extensive experiments, including quantitative and qualitative evaluations on videos of varying lengths (\textit{e.g.}, 3\times and 6\times longer), demonstrate that our method effectively integrates with existing video diffusion models, producing coherent, high-fidelity long videos superior to previous approaches.

Zhen Zeng, Leijiang Gu, Xun Yang et al.

Knowledge editing aims to efficiently and cost-effectively correct inaccuracies and update outdated information. Recently, there has been growing interest in extending knowledge editing from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs), which integrate both textual and visual information, introducing additional editing complexities. Existing multimodal knowledge editing works primarily focus on text-oriented, coarse-grained scenarios, failing to address the unique challenges posed by multimodal contexts. In this paper, we propose a visual-oriented, fine-grained multimodal knowledge editing task that targets precise editing in images with multiple interacting entities. We introduce the Fine-Grained Visual Knowledge Editing (FGVEdit) benchmark to evaluate this task. Moreover, we propose a Multimodal Scope Classifier-based Knowledge Editor (MSCKE) framework. MSCKE leverages a multimodal scope classifier that integrates both visual and textual information to accurately identify and update knowledge related to specific entities within images. This approach ensures precise editing while preserving irrelevant information, overcoming the limitations of traditional text-only editing methods. Extensive experiments on the FGVEdit benchmark demonstrate that MSCKE outperforms existing methods, showcasing its effectiveness in solving the complex challenges of multimodal knowledge editing.

Zhiyuan Han, Beier Zhu, Yanlong Xu et al.

Despite their strong performance in multimodal emotion reasoning, existing Multimodal Large Language Models (MLLMs) often overlook the scenarios involving emotion conflicts, where emotional cues from different modalities are inconsistent. To fill this gap, we first introduce CA-MER, a new benchmark designed to examine MLLMs under realistic emotion conflicts. It consists of three subsets: video-aligned, audio-aligned, and consistent, where only one or all modalities reflect the true emotion. However, evaluations on our CA-MER reveal that current state-of-the-art emotion MLLMs systematically over-rely on audio signal during emotion conflicts, neglecting critical cues from visual modality. To mitigate this bias, we propose MoSEAR, a parameter-efficient framework that promotes balanced modality integration. MoSEAR consists of two modules: (1)MoSE, modality-specific experts with a regularized gating mechanism that reduces modality bias in the fine-tuning heads; and (2)AR, an attention reallocation mechanism that rebalances modality contributions in frozen backbones during inference. Our framework offers two key advantages: it mitigates emotion conflicts and improves performance on consistent samples-without incurring a trade-off between audio and visual modalities. Experiments on multiple benchmarks-including MER2023, EMER, DFEW, and our CA-MER-demonstrate that MoSEAR achieves state-of-the-art performance, particularly under modality conflict conditions.

Xiangchen Yin, Zhenda Yu, Longtao Jiang et al.

While the diffusion transformer (DiT) has become a focal point of interest in recent years, its application in low-light image enhancement remains a blank area for exploration. Current methods recover the details from low-light images while inevitably amplifying the noise in images, resulting in poor visual quality. In this paper, we firstly introduce DiT into the low-light enhancement task and design a novel Structure-guided Diffusion Transformer based Low-light image enhancement (SDTL) framework. We compress the feature through wavelet transform to improve the inference efficiency of the model and capture the multi-directional frequency band. Then we propose a Structure Enhancement Module (SEM) that uses structural prior to enhance the texture and leverages an adaptive fusion strategy to achieve more accurate enhancement effect. In Addition, we propose a Structure-guided Attention Block (SAB) to pay more attention to texture-riched tokens and avoid interference from noisy areas in noise prediction. Extensive qualitative and quantitative experiments demonstrate that our method achieves SOTA performance on several popular datasets, validating the effectiveness of SDTL in improving image quality and the potential of DiT in low-light enhancement tasks.

Long Zhang, Peipei Song, Jianfeng Dong et al.

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos partially relevant to a given query. The core challenge lies in learning robust query-video alignment against spurious semantic correlations arising from inherent data uncertainty: 1) query ambiguity, where the query incompletely characterizes the target video and often contains uninformative tokens, and 2) partial video relevance, where abundant query-irrelevant segments introduce contextual noise in cross-modal alignment. Existing methods often focus on enhancing multi-scale clip representations and retrieving the most relevant clip. However, the inherent data uncertainty in PRVR renders them vulnerable to distractor videos with spurious similarities, leading to suboptimal performance. To fill this research gap, we propose Robust Alignment Learning (RAL) framework, which explicitly models the uncertainty in data. Key innovations include: 1) we pioneer probabilistic modeling for PRVR by encoding videos and queries as multivariate Gaussian distributions. This not only quantifies data uncertainty but also enables proxy-level matching to capture the variability in cross-modal correspondences; 2) we consider the heterogeneous informativeness of query words and introduce learnable confidence gates to dynamically weight similarity. As a plug-and-play solution, RAL can be seamlessly integrated into the existing architectures. Extensive experiments across diverse retrieval backbones demonstrate its effectiveness.

Jiahui Yang, Yongjia Ma, Donglin Di et al.

Existing text-to-image models often rely on parameter fine-tuning techniques such as Low-Rank Adaptation (LoRA) to customize visual attributes. However, when combining multiple LoRA models for content-style fusion tasks, unstructured modifications of weight matrices often lead to undesired feature entanglement between content and style attributes. We propose QR-LoRA, a novel fine-tuning framework leveraging QR decomposition for structured parameter updates that effectively separate visual attributes. Our key insight is that the orthogonal Q matrix naturally minimizes interference between different visual features, while the upper triangular R matrix efficiently encodes attribute-specific transformations. Our approach fixes both Q and R matrices while only training an additional task-specific $ΔR$ matrix. This structured design reduces trainable parameters to half of conventional LoRA methods and supports effective merging of multiple adaptations without cross-contamination due to the strong disentanglement properties between $ΔR$ matrices. Experiments demonstrate that QR-LoRA achieves superior disentanglement in content-style fusion tasks, establishing a new paradigm for parameter-efficient, disentangled fine-tuning in generative models. The project page is available at: https://luna-ai-lab.github.io/QR-LoRA/.

Yunshan Ma, Yujuan Ding, Xun Yang et al.

This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020. We provide an artifact that allows the replication of the experiments using a Python implementation. The artifact is easy to deploy with simple installation, training and evaluation. We reproduce the experiments conducted in the original paper and obtain similar performance as previously reported. The replication results of the experiments support the main claims in the original paper.

Xun Yang, Yunli Wang, Cheng Chen et al.

Recommender systems rely heavily on increasing computation resources to improve their business goal. By deploying computation-intensive models and algorithms, these systems are able to inference user interests and exhibit certain ads or commodities from the candidate set to maximize their business goals. However, such systems are facing two challenges in achieving their goals. On the one hand, facing massive online requests, computation-intensive models and algorithms are pushing their computation resources to the limit. On the other hand, the response time of these systems is strictly limited to a short period, e.g. 300 milliseconds in our real system, which is also being exhausted by the increasingly complex models and algorithms. In this paper, we propose the computation resource allocation solution (CRAS) that maximizes the business goal with limited computation resources and response time. We comprehensively illustrate the problem and formulate such a problem as an optimization problem with multiple constraints, which could be broken down into independent sub-problems. To solve the sub-problems, we propose the revenue function to facilitate the theoretical analysis, and obtain the optimal computation resource allocation strategy. To address the applicability issues, we devise the feedback control system to help our strategy constantly adapt to the changing online environment. The effectiveness of our method is verified by extensive experiments based on the real dataset from Taobao.com. We also deploy our method in the display advertising system of Alibaba. The online results show that our computation resource allocation solution achieves significant business goal improvement without any increment of computation cost, which demonstrates the efficacy of our method in real industrial practice.

Qi Zheng, Jianfeng Dong, Xiaoye Qu et al.

This paper targets the task of language-based video moment localization. The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, and then match them with the given query to determine the target moment. However, candidate moments generated with a fixed temporal granularity may be suboptimal to handle the large variation in moment lengths. To this end, we propose a novel multi-stage Progressive Localization Network (PLN) which progressively localizes the target moment in a coarse-to-fine manner. Specifically, each stage of PLN has a localization branch, and focuses on candidate moments that are generated with a specific temporal granularity. The temporal granularities of candidate moments are different across the stages. Moreover, we devise a conditional feature manipulation module and an upsampling connection to bridge the multiple localization branches. In this fashion, the later stages are able to absorb the previously learned information, thus facilitating the more fine-grained localization. Extensive experiments on three public datasets demonstrate the effectiveness of our proposed PLN for language-based moment localization, especially for localizing short moments in long videos.

Jianfeng Dong, Xirong Li, Chaoxi Xu et al.

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method.

Xun Yang, Jianfeng Dong, Yixin Cao et al.

The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos. Specifically, given a complex user query, we first recursively compose a latent semantic tree to structurally describe the text query. We then design a tree-augmented query encoder to derive structure-aware query representation and a temporal attentive video encoder to model the temporal characteristics of videos. Finally, both the query and videos are mapped into a joint embedding space for matching and ranking. In this approach, we have a better understanding and modeling of the complex queries, thereby achieving a better video retrieval performance. Extensive experiments on large scale video retrieval benchmark datasets demonstrate the effectiveness of our approach.

Yunshan Ma, Yujuan Ding, Xun Yang et al.

Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed KERN model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.

Yunshan Ma, Xun Yang, Lizi Liao et al.

Fashion knowledge helps people to dress properly and addresses not only physiological needs of users, but also the demands of social activities and conventions. It usually involves three mutually related aspects of: occasion, person and clothing. However, there are few works focusing on extracting such knowledge, which will greatly benefit many downstream applications, such as fashion recommendation. In this paper, we propose a novel method to automatically harvest fashion knowledge from social media. We unify three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata. For person detection and analysis, we use the off-the-shelf tools due to their flexibility and satisfactory performance. For clothing recognition and occasion prediction, we unify the two tasks by using a contextualized fashion concept learning module, which captures the dependencies and correlations among different fashion concepts. To alleviate the heavy burden of human annotations, we introduce a weak label modeling module which can effectively exploit machine-labeled data, a complementary of clean data. In experiments, we contribute a benchmark dataset and conduct extensive experiments from both quantitative and qualitative perspectives. The results demonstrate the effectiveness of our model in fashion concept prediction, and the usefulness of extracted knowledge with comprehensive analysis.

Lizi Liao, Ryuichi Takanobu, Yunshan Ma et al.

When traveling to a foreign country, we are often in dire need of an intelligent conversational agent to provide instant and informative responses to our various queries. However, to build such a travel agent is non-trivial. First of all, travel naturally involves several sub-tasks such as hotel reservation, restaurant recommendation and taxi booking etc, which invokes the need for global topic control. Secondly, the agent should consider various constraints like price or distance given by the user to recommend an appropriate venue. In this paper, we present a Deep Conversational Recommender (DCR) and apply to travel. It augments the sequence-to-sequence (seq2seq) models with a neural latent topic component to better guide response generation and make the training easier. To consider the various constraints for venue recommendation, we leverage a graph convolutional network (GCN) based approach to capture the relationships between different venues and the match between venue and dialog context. For response generation, we combine the topic-based component with the idea of pointer networks, which allows us to effectively incorporate recommendation results. We perform extensive evaluation on a multi-turn task-oriented dialog dataset in travel domain and the results show that our method achieves superior performance as compared to a wide range of baselines.

Xun Yang, Meng Wang, Dacheng Tao

Despite the promising progress made in recent years, person re-identification remains a challenging task due to complex variations in human appearances from different camera views. This paper presents a logistic discriminant metric learning method for this challenging problem. Different with most existing metric learning algorithms, it exploits both original data and auxiliary data during training, which is motivated by the new machine learning paradigm - Learning Using Privileged Information. Such privileged information is a kind of auxiliary knowledge which is only available during training. Our goal is to learn an optimal distance function by constructing a locally adaptive decision rule with the help of privileged information. We jointly learn two distance metrics by minimizing the empirical loss penalizing the difference between the distance in the original space and that in the privileged space. In our setting, the distance in the privileged space functions as a local decision threshold, which guides the decision making in the original space like a teacher. The metric learned from the original space is used to compute the distance between a probe image and a gallery image during testing. In addition, we extend the proposed approach to a multi-view setting which is able to explore the complementation of multiple feature representations. In the multi-view setting, multiple metrics corresponding to different original features are jointly learned, guided by the same privileged information. Besides, an effective iterative optimization scheme is introduced to simultaneously optimize the metrics and the assigned metric weights. Experiment results on several widely-used datasets demonstrate that the proposed approach is superior to global decision threshold based methods and outperforms most state-of-the-art results.

Xun Yang, Yunshan Ma, Lizi Liao et al.

Identifying mix-and-match relationships between fashion items is an urgent task in a fashion e-commerce recommender system. It will significantly enhance user experience and satisfaction. However, due to the challenges of inferring the rich yet complicated set of compatibility patterns in a large e-commerce corpus of fashion items, this task is still underexplored. Inspired by the recent advances in multi-relational knowledge representation learning and deep neural networks, this paper proposes a novel Translation-based Neural Fashion Compatibility Modeling (TransNFCM) framework, which jointly optimizes fashion item embeddings and category-specific complementary relations in a unified space via an end-to-end learning manner. TransNFCM places items in a unified embedding space where a category-specific relation (category-comp-category) is modeled as a vector translation operating on the embeddings of compatible items from the corresponding categories. By this way, we not only capture the specific notion of compatibility conditioned on a specific pair of complementary categories, but also preserve the global notion of compatibility. We also design a deep fashion item encoder which exploits the complementary characteristic of visual and textual features to represent the fashion products. To the best of our knowledge, this is the first work that uses category-specific complementary relations to model the category-aware compatibility between items in a translation-based embedding space. Extensive experiments demonstrate the effectiveness of TransNFCM over the state-of-the-arts on two real-world datasets.

Di Wu, Cheng Chen, Xun Yang et al.

In online display advertising, guaranteed contracts and real-time bidding (RTB) are two major ways to sell impressions for a publisher. Despite the increasing popularity of RTB, there is still half of online display advertising revenue generated from guaranteed contracts. Therefore, simultaneously selling impressions through both guaranteed contracts and RTB is a straightforward choice for a publisher to maximize its yield. However, deriving the optimal strategy to allocate impressions is not a trivial task, especially when the environment is unstable in real-world applications. In this paper, we formulate the impression allocation problem as an auction problem where each contract can submit virtual bids for individual impressions. With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts. Since the bids from contracts are decided by the publisher, we propose a multi-agent reinforcement learning (MARL) approach to derive cooperative policies for the publisher to maximize its yield in an unstable environment. The proposed approach also resolves the common challenges in MARL such as input dimension explosion, reward credit assignment, and non-stationary environment. Experimental evaluations on large-scale real datasets demonstrate the effectiveness of our approach.

Xun Yang, Meng Wang, Richang Hong et al.

Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms have been developed in the fully-supervised setting, requiring access to a large amount of labeled training data. However, the main bottleneck for fully-supervised re-ID is the limited availability of labeled training samples. To address this problem, in this paper, we propose a self-trained subspace learning paradigm for person re-ID which effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched. The proposed approach first constructs pseudo pairwise relationships among unlabeled persons using the k-nearest neighbors algorithm. Then, with the pseudo pairwise relationships, the unlabeled samples can be easily combined with the labeled samples to learn a discriminative projection by solving an eigenvalue problem. In addition, we refine the pseudo pairwise relationships iteratively, which further improves the learning performance. A multi-kernel embedding strategy is also incorporated into the proposed approach to cope with the non-linearity in person's appearance and explore the complementation of multiple kernels. In this way, the performance of person re-ID can be greatly enhanced when training data are insufficient. Experimental results on six widely-used datasets demonstrate the effectiveness of our approach and its performance can be comparable to the reported results of most state-of-the-art fully-supervised methods while using much fewer labeled data.