论文检索

Lu Xu, Guosheng Yin

Fully decentralized deep learning removes global servers and ensures local data privacy. However, Euclidean consensus, averaging weights, gradients or momentum, may degrade under the situations with non-i.i.d. (non-independent and identically distributed) data and client size imbalance. We propose a geometry-aware approach based on natural gradient variational inference. Clients communicate in the expectation parameter space of an exponential family, where simple linear mixing yields a forward Kullback--Leibler (KL) barycenter consensus. The aggregate is the model closest to all client distributions, aligning updates across heterogeneous sites and mitigating distribution shift. We further provide a lightweight decentralized Adam implementation where each client maintains a diagonal Gaussian posterior and operates entirely in the expectation space for both optimization and consensus. We prove convergence for convex losses on connected graphs. On CIFAR-100 and a medical image segmentation benchmark, our method substantially outperforms Euclidean-space consensus baselines under severe non-i.i.d. and client-imbalance cases, achieving around 20% accuracy gain on CIFAR-100, while matching the communication budget and improving training stability. The code is available at https://github.com/x-lu/Beyond-euclidean-gossip.

Shivanshu Shekhar, Uttaran Bhattacharya, Raghavendra Addanki, Mehrab Tanjim, Somdeb Sarkhel, Tong Zhang

Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but these models struggle to capture subtle temporal dynamics. We propose a fundamentally different approach: repurposing video generative models, which are inherently designed to model temporal structure, as reward models. We present the Generative-Transformer-based Self-Supervised Video Judge (\modelname), a novel evaluation model that transforms state-of-the-art video generation models into powerful temporally-aware reward models. Our key insight is that generative models can be reformulated as energy-based models (EBMs) that assign low energy to high-quality videos and high energy to degraded ones, enabling them to discriminate video quality with remarkable precision when trained via contrastive objectives. To prevent the model from exploiting superficial differences between real and generated videos, we design challenging synthetic negative videos through controlled latent-space perturbations: temporal slicing, feature swapping, and frame shuffling, which simulate realistic but subtle visual degradations. This forces the model to learn meaningful spatiotemporal features rather than trivial artifacts. \modelname achieves state-of-the-art performance on GenAI-Bench and MonteBench using only 30K human-annotations: 6xto 65xfewer than existing VLM-based approaches.

Nicolas Michel, Maorong Wang, Jiangpeng He, Toshihiko Yamasaki

Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Distillation (CD), where a student learns sequentially from a stream of teacher models without retaining access to earlier teachers. CD faces two challenges: teacher training data is unavailable, and teachers have varying expertise. We show that external unlabeled data enables Unseen Knowledge Transfer (UKT), allowing the student to acquire information from domains not present in the training data, while known to the teacher. We also show that sequential distillation causes Unseen Knowledge Forgetting (UKF) when transferred knowledge is lost after training on later teachers. To better trade off between UKT and UKF, we propose Self External Data Distillation (SE2D), a method that preserves logits on external data to stabilize learning across heterogeneous teachers. Experiments on multiple benchmarks show that SE2D reduces UKF and improves cross-domain generalization. The code and implementation for this work are publicly available at: https://github.com/Nicolas1203/continual_distillation

Yuanlin Wang, Ruiqin Xiong, Jiyu Xie, Zhenkun Zhu, Zhaofei Yu, Xiaopeng Fan, Tiejun Huang

Spike camera is a neuromorphic vision sensor with ultra-high temporal resolution, capable of capturing fast-moving scenes by firing a stream of binary spikes. However, its relatively low spatial resolution limits the acquisition of fine-grained visual details, motivating research on spike camera super resolution (SCSR). Existing SCSR methods typically operate on fixed-length spike sequences, where the accessible information is restricted to a local temporal neighborhood. Moreover, spike fluctuations hinder reliable intensity extraction. Both factors affect the performance of SCSR. To address these issues, we propose a hierarchical recurrent network named Spk2VidNet to reconstruct high-fidelity high resolution image sequences from low resolution spike data. To mitigate fluctuations, Spk2VidNet progressively exploits temporal correlations within spike stream to enhance feature representation by hierarchically enlarging temporal receptive fields. Within the recurrent block, we introduce an alignment module that leverages the motion consistency among multiple frames to jointly estimate and mutually refine inter-frame motions, achieving more accurate temporal alignment. In addition, we develop a fusion module to adaptively integrate neighboring aligned features based on multi-scale similarity for robust feature aggregation. We further propose a segment-wise training with state transfer strategy to efficiently model long-term dependencies with limited GPU memory. Experiments on synthetic and real-captured spike data demonstrate that Spk2VidNet achieves state-of-the-art performance.

Yanzhe Lyu, Chen Geng, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu

Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies.

Bohan Jia, Wenxuan Huang, Yuntian Tang, Junbo Qiao, Jincheng Liao, Shaosheng Cao, Fei Zhao, Zhaopeng Feng, Zhouhong Gu, Zhenfei Yin 等

While real-world applications increasingly demand intricate scene manipulation, existing instruction-guided image editing benchmarks often oversimplify task complexity and lack comprehensive, fine-grained instructions. To bridge this gap, we introduce CompBench, a large-scale benchmark specifically designed for complex instruction-guided image editing. CompBench features challenging editing scenarios that incorporate fine-grained instruction following, spatial and contextual reasoning, thereby enabling comprehensive evaluation of image editing models' precise manipulation capabilities. To construct CompBench, we propose an MLLM-human collaborative framework with tailored task pipelines. Furthermore, we propose an instruction decoupling strategy that disentangles editing intents into four key dimensions: location, appearance, dynamics, and objects, ensuring closer alignment between instructions and complex editing requirements. Extensive evaluations reveal that CompBench exposes fundamental limitations of current image editing models and provides critical insights for the development of next-generation instruction-guided image editing systems. Our project page is available at https://comp-bench.github.io/.

Zhengxian Yang, Fei Xie, Xutao Xue, Rui Zhang, Taicheng Huang, Yang Liu, Mengqi Ji, Tao Yu

3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with their wider field of view (FOV), promise high-quality reconstructions from fewer inputs and have recently attracted much attention. However, since 3DGS relies on rasterization, most subsequent works involving fisheye camera inputs first undistort images before training, which introduces two problems: 1) Black borders at image edges cause information loss and negate the fisheye's large FOV advantage; 2) Undistortion's stretch-and-interpolate resampling spreads each pixel's value over a larger area, diluting detail density-- causes 3DGS overfitting these low-frequency zones, producing blur and floating artifacts. In this work, we integrate fisheye camera model into the original 3DGS framework, enabling native fisheye image input for training without preprocessing. Despite correct modeling, we observed that the reconstructed scenes still exhibit floaters at image edges: Distortion increases toward the periphery, and 3DGS's original per-iteration random-selecting-view optimization ignores the cross-view correlations of a Gaussian, leading to extreme shapes (e.g., oversized or elongated) that degrade reconstruction quality. To address this, we introduce a feature-overlap-driven cross-view joint optimization strategy that establishes consistent geometric and photometric constraints across views--a technique equally applicable to existing pinhole-camera-based pipelines. Our DirectFisheye-GS matches or surpasses state-of-the-art performance on public datasets.

Jie Xiao, Yinchao Ma, Yuyang Tang, Dengqing Yang, Jianpeng Yang, Xu Zhou, Qiao Li, Wenfei Yang, Tianzhu Zhang

3D single object tracking (SOT) in point clouds is essential for real-world 3D perception, yet it remains challenging due to data sparsity and large variations in scale and structure across diverse object categories. Most existing methods rely on a category-specific paradigm that trains separate models for each class, severely limiting scalability and generalization in real deployment. Extending these methods to a single model capable of tracking diverse object categories proves inadequate, as the significant variations across categories make it difficult to establish reliable geometric correspondences without category-specific priors. To overcome these limitations, we propose a Unified Structural KeyPoint Tracker (UniKPT), a novel structure-aware and generalizable framework for category-unified 3D point cloud tracking. UniKPT comprises three key modules: (1) an adaptive keypoint extractor that produces scale-aware and semantically meaningful keypoints; (2) a progressive correspondence aligner that establishes robust cross-frame geometric associations; and (3) a confidence-aware structural localization module that suppresses unreliable matches and leverages fine-grained structural relationships for precise 3D localization. Extensive experiments on the nuScenes and KITTI benchmarks show that UniKPT achieves new state-of-the-art performance in category-unified 3D SOT. On the challenging nuScenes dataset, our unified model further surpasses category-specific state-of-the-art trackers by 4.37% in Success and 5.16% in Precision.

Zeyi Huang, Yuyang Ji, Xiaofang Wang, Nikhil Mehta, Tong Xiao, Donghyun Lee, Sigmund Vanvalkenburgh, Shengxin Zha, Bolin Lai, Licheng Yu 等

Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited context windows. In this work, we introduce VideoMindPalace, a new framework inspired by the "Mind Palace", which organizes critical video moments into a topologically structured semantic graph. VideoMindPalace organizes key information through (i) hand-object tracking and interaction, (ii) clustered activity zones representing specific areas of recurring activities, and (iii) environment layout mapping, allowing natural language parsing by LLMs to provide grounded insights on spatio-temporal and 3D context. In addition, we propose the Video MindPalace Benchmark (VMB), to assess human-like reasoning, including spatial localization, temporal reasoning, and layout-aware sequential understanding. Evaluated on VMB and established video QA datasets, including EgoSchema, NExT-QA, IntentQA, and the Active Memories Benchmark, VideoMindPalace demonstrates notable gains in spatio-temporal coherence and human-aligned reasoning, advancing long-form video analysis capabilities in VLMs.

Pei Geng, Jian Yang, Shanshan Zhang

Human-Object Interaction (HOI) detection aims to predict the <Human, Interaction, Object> triplets, where the core challenge lies in recognizing the interaction of each human-object pair. Despite recent progress thanks to more advanced model architectures, HOI performance remains unsatisfactory. In this work, we first perform some failure analysis and find that the accuracy of the no-interaction category is extremely low, largely hindering the improvement of overall performance. We further look into the error types and find the mis-classification between no-interaction and with-interaction ones can be handled by human-object relation priors. Specifically, to better distinguish no-interaction from direct interactions, we propose 3D location prior, which indicates the distance between human and object; as of no-interaction vs. indirect interactions, we propose gaze area prior, which denotes whether human can see the object or not. The above two types of human-object relation priors are represented by text and are combined with the original visual features, generating multi-modal cues for interaction recognition.Experimental results on the HICO-DET and V-COCO datasets demonstrate that our proposed human-object relation priors are effective and our method HORP surpasses previous methods under various settings and scenarios. In particular, the usage of our priors significantly enhances the model's recognition ability for the no-interaction category.

Shunxin Wang, Raymond Veldhuis, Nicola Strisciuglio

Frequency shortcuts refer to specific frequency patterns that models heavily rely on for correct classification. Previous studies have shown that models trained on small image datasets often exploit such shortcuts, potentially impairing their generalization performance. However, existing methods for identifying frequency shortcuts require expensive computations and become impractical for analyzing models trained on large datasets. In this work, we propose the first approach to more efficiently analyze frequency shortcuts at a large scale. We show that both CNN and transformer models learn frequency shortcuts on ImageNet. We also expose that frequency shortcut solutions can yield good performance on out-of-distribution (OOD) test sets which largely retain texture information. However, these shortcuts, mostly aligned with texture patterns, hinder model generalization on rendition-based OOD test sets. These observations suggest that current OOD evaluations often overlook the impact of frequency shortcuts on model generalization. Future benchmarks could thus benefit from explicitly assessing and accounting for these shortcuts to build models that generalize across a broader range of OOD scenarios.

Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Junlin Han, Ender Konukoglu, Serge Belongie

Generalized few-shot 3D point cloud segmentation (GFS-PCS) adapts models to new classes with few support samples while retaining base class segmentation. Existing GFS-PCS methods enhance prototypes via interacting with support or query features but remain limited by sparse knowledge from few-shot samples. Meanwhile, 3D vision-language models (3D VLMs), generalizing across open-world novel classes, contain rich but noisy novel class knowledge. In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL. Specifically, we present a prototype-guided pseudo-label selection to filter low-quality regions, followed by an adaptive infilling strategy that combines knowledge from pseudo-label contexts and few-shot samples to adaptively label the filtered, unlabeled areas. Additionally, we design a novel-base mix strategy to embed few-shot samples into training scenes, preserving essential context for improved novel class learning. Moreover, recognizing the limited diversity in current GFS-PCS benchmarks, we introduce two challenging benchmarks with diverse novel classes for comprehensive generalization evaluation. Experiments validate the effectiveness of our framework across models and datasets. Our approach and benchmarks provide a solid foundation for advancing GFS-PCS in the real world. The code is at here.

Ding Ding, Yueming Pan, Ruoyu Feng, Qi Dai, Kai Qiu, Jianmin Bao, Chong Luo, Zhenzhong Chen

In this paper, we present HomoGen, an enhanced video inpainting method based on homography propagation and diffusion models. HomoGen leverages homography registration to propagate contextual pixels as priors for generating missing content in corrupted videos. Unlike previous flow-based propagation methods, which introduce local distortions due to point-to-point optical flows, homography-induced artifacts are typically global structural distortions that preserve semantic integrity. To effectively utilize these priors for generation, we employ a video diffusion model that inherently prioritizes semantic information within the priors over pixel-level details. A content-adaptive control mechanism is proposed to scale and inject the priors into intermediate video latents during iterative denoising. In contrast to existing transformer-based networks that often suffer from artifacts within priors, leading to error accumulation and unrealistic results, our denoising diffusion network can smooth out artifacts and ensure natural outputs. Extensive experiments demonstrate the effectiveness of the proposed method qualitatively and quantitatively.

Ziyi Liu, Yangcen Liu

Weakly-supervised Temporal Action Localization (WTAL) has achieved notable success but still suffers from a lack of temporal annotations, leading to a performance and framework gap compared with fully-supervised methods. While recent approaches employ pseudo labels for training, three key challenges: generating high-quality pseudo labels, making full use of different priors, and optimizing training methods with noisy labels remain unresolved. Due to these perspectives, we propose PseudoFormer, a novel two-branch framework that bridges the gap between weakly and fully-supervised Temporal Action Localization (TAL). We first introduce RickerFusion, which maps all predicted action proposals to a global shared space to generate pseudo labels with better quality. Subsequently, we leverage both snippet-level and proposal-level labels with different priors from the weak branch to train the regression-based model in the full branch. Finally, the uncertainty mask and iterative refinement mechanism are applied for training with noisy pseudo labels. PseudoFormer achieves state-of-the-art WTAL results on the two commonly used benchmarks, THUMOS14 and ActivityNet1.3. Besides, extensive ablation studies demonstrate the contribution of each component of our method.

Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu

Learned image compression (LIC) using deep learning architectures has seen significant advancements, yet standard rate-distortion (R-D) optimization often encounters imbalanced updates due to diverse gradients of the rate and distortion objectives. This imbalance can lead to suboptimal optimization, where one objective dominates, thereby reducing overall compression efficiency. To address this challenge, we reformulate R-D optimization as a multi-objective optimization (MOO) problem and introduce two balanced R-D optimization strategies that adaptively adjust gradient updates to achieve more equitable improvements in both rate and distortion. The first proposed strategy utilizes a coarse-to-fine gradient descent approach along standard R-D optimization trajectories, making it particularly suitable for training LIC models from scratch. The second proposed strategy analytically addresses the reformulated optimization as a quadratic programming problem with an equality constraint, which is ideal for fine-tuning existing models. Experimental results demonstrate that both proposed methods enhance the R-D performance of LIC models, achieving around a 2% BD-Rate reduction with acceptable additional training cost, leading to a more balanced and efficient optimization process. Code will be available at https://gitlab.com/viper-purdue/Balanced-RD.

Peijie Wang, Zhong-Zhi Li, Fei Yin, Dekang Ran, Cheng-Lin Liu

Multimodal Large Language Models (MLLMs) have shown promising capabilities in mathematical reasoning within visual contexts across various datasets. However, most existing multimodal math benchmarks are limited to single-visual contexts, which diverges from the multi-visual scenarios commonly encountered in real-world mathematical applications. To address this gap, we introduce MV-MATH: a meticulously curated dataset of 2,009 high-quality mathematical problems. Each problem integrates multiple images interleaved with text, derived from authentic K-12 scenarios and enriched with detailed annotations. MV-MATH includes multiple-choice, free-form, and multi-step questions, covering 11 subject areas across 3 difficulty levels, and serves as a comprehensive and rigorous benchmark for assessing MLLMs' mathematical reasoning in multi-visual contexts. Through extensive experimentation, we observe that MLLMs encounter substantial challenges in multi-visual math tasks, with a considerable performance gap relative to human capabilities on MV-MATH. Furthermore, we analyze the performance and error patterns of various models, providing insights into MLLMs' mathematical reasoning capabilities within multi-visual settings.

Jingyi Zhou, Peng Ye, Haoyu Zhang, Jiakang Yuan, Rao Qiang, Liu YangChenXu, Wu Cailin, Feng Xu, Tao Chen

Iterative-based methods have become mainstream in stereo matching due to their high performance. However, these methods heavily rely on labeled data and face challenges with unlabeled real-world data. To this end, we propose a consistency-aware self-training framework for iterative-based stereo matching for the first time, leveraging real-world unlabeled data in a teacher-student manner. We first observe that regions with larger errors tend to exhibit more pronounced oscillation characteristics during model prediction.Based on this, we introduce a novel consistency-aware soft filtering module to evaluate the reliability of teacher-predicted pseudo-labels, which consists of a multi-resolution prediction consistency filter and an iterative prediction consistency filter to assess the prediction fluctuations of multiple resolutions and iterative optimization respectively. Further, we introduce a consistency-aware soft-weighted loss to adjust the weight of pseudo-labels accordingly, relieving the error accumulation and performance degradation problem due to incorrect pseudo-labels. Extensive experiments demonstrate that our method can improve the performance of various iterative-based stereo matching approaches in various scenarios. In particular, our method can achieve further enhancements over the current SOTA methods on several benchmark datasets.

Mohd Hozaifa Khan, Ravi Kiran Sarvadevabhatla

We introduce Sketchtopia, a large-scale dataset and AI framework designed to explore goal-driven, multimodal communication through asynchronous interactions in a Pictionary-inspired setup. Sketchtopia captures natural human interactions, including freehand sketches, open-ended guesses, and iconic feedback gestures, showcasing the complex dynamics of cooperative communication under constraints. It features over 20K gameplay sessions from 916 players, capturing 263K sketches, 10K erases, 56K guesses and 19.4K iconic feedbacks. We introduce multimodal foundational agents with capabilities for generative sketching, guess generation and asynchronous communication. Our dataset also includes 800 human-agent sessions for benchmarking the agents. We introduce novel metrics to characterize collaborative success, responsiveness to feedback and inter-agent asynchronous communication. Sketchtopia pushes the boundaries of multimodal AI, establishing a new benchmark for studying asynchronous, goal-oriented interactions between humans and AI agents. The dataset can be found at https://sketchtopia25.github.io/

Min Jung Lee, Dayoung Gong, Minsu Cho

The exponential increase in video content poses significant challenges in terms of efficient navigation, search, and retrieval, thus requiring advanced video summarization techniques. Existing video summarization methods, which heavily rely on visual features and temporal dynamics, often fail to capture the semantics of video content, resulting in incomplete or incoherent summaries. To tackle the challenge, we propose a new video summarization framework that leverages the capabilities of recent Large Language Models (LLMs), expecting that the knowledge learned from massive data enables LLMs to evaluate video frames in a manner that better aligns with diverse semantics and human judgments, effectively addressing the inherent subjectivity in defining keyframes. Our method, dubbed LLM-based Video Summarization (LLMVS), translates video frames into a sequence of captions using a Muti-modal Large Language Model (M-LLM) and then assesses the importance of each frame using an LLM, based on the captions in its local context. These local importance scores are refined through a global attention mechanism in the entire context of video captions, ensuring that our summaries effectively reflect both the details and the overarching narrative. Our experimental results demonstrate the superiority of the proposed method over existing ones in standard benchmarks, highlighting the potential of LLMs in the processing of multimedia content.

Xinan Xie, Qing Zhang, Wei-Shi Zheng

While event-based deblurring have demonstrated impressive results, they are impractical for consumer photos captured by cell phones and digital cameras that are not equipped with the event sensor. To address this problem, we in this paper propose a novel deblurring framework called Event Generation Deblurring (EGDeblurring), which allows to effectively deblur an image by generating event guidance describing the motion information using a diffusion model. Specifically, we design a motion prior generation diffusion model and a feature extractor to produce prior information beneficial for deblurring, rather than generating the raw event representation. In order to achieve effective fusion of motion prior information with blurry images and produce high-quality results, we develop a regression deblurring network embedded with a dual-attention channel fusion block. Experiments on multiple datasets demonstrate that our method outperforms state-of-the-art image deblurring methods. Our code is available at https://github.com/XinanXie/EGDeblurring https://github.com/XinanXie/EGDeblurring.