English
Related papers

Related papers: KTV: Keyframes and Key Tokens Selection for Effici…

200 papers

This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Feng Wang , Yichun Shi , Ceyuan Yang , Qiushan Guo , Jingxiang Sun , Alan Yuille , Peng Wang

Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Hong Gao , Yiming Bao , Xuezhen Tu , Bin Zhong , Linan Yue , Minling Zhang

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of processing dense frame sequences. Prevailing solutions, which select a keyframe subset,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Shaoguang Wang , Weiyu Guo , Ziyang Chen , Xuming Hu , Hui Xiong

Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Hong Gao , Yiming Bao , Xuezhen Tu , Yutong Xu , Yue Jin , Yiyang Mu , Bin Zhong , Linan Yue , Min-Ling Zhang

Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Sitong Gong , Yunzhi Zhuge , Lu Zhang , Zongxin Yang , Pingping Zhang , Huchuan Lu

Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods employ post-hoc low-response token pruning in decoder layers,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yongdong Luo , Wang Chen , Xiawu Zheng , Weizhong Huang , Shukang Yin , Haojia Lin , Chaoyou Fu , Jinfa Huang , Jiayi Ji , Jiebo Luo , Rongrong Ji

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Zhuqiang Lu , Zhenfei Yin , Mengwei He , Zhihui Wang , Zicheng Liu , Zhiyong Wang , Kun Hu

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Haokui Zhang , Congyang Ou , Dawei Yan , Peng Wang , Qingsen Yan , Yu Zhang , Ying Li , Rong Xiao

Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ziyang Fan , Keyu Chen , Ruilong Xing , Yulin Li , Li Jiang , Zhuotao Tian

Video understanding in multimodal large language models requires selecting informative frames from long, redundant videos under limited visual-token budgets. Existing methods often rely on uniform sampling, point-wise relevance scoring,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Jingfeng Chen , Jiawen Qian , Wendi Deng , Yinuo Guo , Jiaqi Yu , Sicong Leng , Raghuveer Thirukovalluru , Bhuwan Dhingra

While significant advancements have been made in compressed representations for text embeddings in large language models (LLMs), the compression of visual tokens in multi-modal LLMs (MLLMs) has remained a largely overlooked area. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Jieneng Chen , Luoxin Ye , Ju He , Zhao-Yang Wang , Daniel Khashabi , Alan Yuille

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Yefei He , Feng Chen , Jing Liu , Wenqi Shao , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sara Ghazanfari , Francesco Croce , Nicolas Flammarion , Prashanth Krishnamurthy , Farshad Khorrami , Siddharth Garg

Understanding long-form videos remains a significant challenge for vision--language models (VLMs) due to their extensive temporal length and high information density. Most current multimodal large language models (MLLMs) rely on uniform…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Xian Zhang , Zexi Wu , Zinuo Li , Hongming Xu , Luqi Gong , Farid Boussaid , Naoufel Werghi , Mohammed Bennamoun

Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Chao Wang , Xudong Tan , Jianjian Cao , Kangcong Li , Tao Chen

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Zeliang Zhang , Phu Pham , Wentian Zhao , Kun Wan , Yu-Jhe Li , Jianing Zhou , Daniel Miranda , Ajinkya Kale , Chenliang Xu

Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence length and thousands of visual tokens contributed by…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Wengyi Zhan , Mingbao Lin , Zhihang Lin , Rongrong Ji

Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhanced streaming audio-visual large language model that processes…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Guangzhi Sun , Yixuan Li , Xiaodong Wu , Yudong Yang , Wei Li , Zejun Ma , Chao Zhang

Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xinyue Hao , Gen Li , Shreyank N Gowda , Robert B Fisher , Jonathan Huang , Anurag Arnab , Laura Sevilla-Lara

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