English
Related papers

Related papers: Fre-Res: Frequency-Residual Video Token Compressio…

200 papers

Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Yadang Chen , Wentao Zhu , Zhi-Xin Yang , Enhua Wu

Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Zhengjian Kang , Qi Chen , Rui Liu , Kangtong Mo , Xingyu Zhang , Xiaoyu Deng , Ye Zhang

Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Jingchao Wang , Zhijian Wu , Dingjiang Huang , Yefeng Zheng , Hong Wang

In order to be able to deliver today's voluminous amount of video contents through limited bandwidth channels in a perceptually optimal way, it is important to consider perceptual trade-offs of compression and space-time downsampling…

Image and Video Processing · Electrical Eng. & Systems 2021-04-01 Dae Yeol Lee , Hyunsuk Ko , Jongho Kim , Alan C. Bovik

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta

Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Yanan Guo , Wenhui Dong , Jun Song , Shiding Zhu , Xuan Zhang , Hanqing Yang , Yingbo Wang , Yang Du , Xianing Chen , Bo Zheng

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Test-time scaling (TTS) has become a prevalent technique in image generation, significantly boosting output quality by expanding the number of parallel samples and filtering them using pre-trained reward models. However, applying this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Hang Xu , Linjiang Huang , Feng Zhao

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment specific objects in videos based on natural language expressions involving audio, vision, and text information. This task poses significant challenges in cross-modal reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Dian Jin , Yanghao Zhou , Jinxing Zhou , Jiaqi Ma , Ruohao Guo , Dan Guo

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains. To address this limitation, we propose LaCo (Layer-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Juntao Liu , Liqiang Niu , Wenchao Chen , Jie Zhou , Fandong Meng

Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Xinhao Li , Ziang Yan , Desen Meng , Lu Dong , Xiangyu Zeng , Yinan He , Yali Wang , Yu Qiao , Yi Wang , Limin Wang

This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs'…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Yi Wang , Xinhao Li , Ziang Yan , Yinan He , Jiashuo Yu , Xiangyu Zeng , Chenting Wang , Changlian Ma , Haian Huang , Jianfei Gao , Min Dou , Kai Chen , Wenhai Wang , Yu Qiao , Yali Wang , Limin Wang

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial…

Computer Vision and Pattern Recognition · Computer Science 2015-04-08 Zuxuan Wu , Xi Wang , Yu-Gang Jiang , Hao Ye , Xiangyang Xue

Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Shaobo Ju , Baiyang Song , Tao Chen , Jiapeng Zhang , Qiong Wu , Chao Chang , HuaiXi Wang , Yiyi Zhou , Rongrong Ji

Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Hao Tang , Chengchao Shen

Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Lianying Chao , Linfeng Yin , Peiyu Ren , Yifan Jiang , Qiaoyu Ren , Dingcheng Shan , Jing-cheng Pang , Sijie Wu , Xubin Li , Kai Zhang , Xin Chen

The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction --…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jihwan Kim , Nikhil Parthasarathy , Danfeng Qin , Junhwa Hur , Deqing Sun , Bohyung Han , Ming-Hsuan Yang , Boqing Gong

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Xinkui Zhao , Zuxin Wang , Yifan Zhang , Guanjie Cheng , Yueshen Xu , Shuiguang Deng , Chang Liu , Naibo Wang , Jianwei Yin

Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Yupeng Zhou , Zhen Li , Ziheng Ouyang , Yuming Chen , Ruoyi Du , Daquan Zhou , Bin Fu , Yihao Liu , Peng Gao , Ming-Ming Cheng , Qibin Hou