English
Related papers

Related papers: Multimodal Long Video Modeling Based on Temporal D…

200 papers

Video language models (VideoLMs) have made significant progress in multimodal understanding. However, temporal understanding, which involves identifying event order, duration, and relationships across time, still remains a core challenge.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yumeng Shi , Quanyu Long , Yin Wu , Wenya Wang

Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence. Existing methods mainly tackle this task via matching and aligning semantics between a sentence…

Computer Vision and Pattern Recognition · Computer Science 2019-11-01 Yitian Yuan , Lin Ma , Jingwen Wang , Wei Liu , Wenwu Zhu

Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Chao-Yuan Wu , Philipp Krähenbühl

Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Xi Tang , Jihao Qiu , Lingxi Xie , Yunjie Tian , Jianbin Jiao , Qixiang Ye

Recently, integrating visual foundation models into large language models (LLMs) to form video understanding systems has attracted widespread attention. Most of the existing models compress diverse semantic information within the whole…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Dingxin Cheng , Mingda Li , Jingyu Liu , Yongxin Guo , Bin Jiang , Qingbin Liu , Xi Chen , Bo Zhao

Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a…

Computation and Language · Computer Science 2024-10-18 Sijun Tan , Xiuyu Li , Shishir Patil , Ziyang Wu , Tianjun Zhang , Kurt Keutzer , Joseph E. Gonzalez , Raluca Ada Popa

Video data, especially long-form video, is extremely dense and high-dimensional. Text-based summaries of video content offer a way to represent query-relevant content in a much more compact manner than raw video. In addition, textual…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Kuleen Sasse , Efsun Sarioglu Kayi , Arun Reddy

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…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Min Jung Lee , Dayoung Gong , Minsu Cho

It is desirable but challenging to generate content-rich long videos in the scale of minutes. Autoregressive large language models (LLMs) have achieved great success in generating coherent and long sequences of tokens in the domain of…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Yuqing Wang , Tianwei Xiong , Daquan Zhou , Zhijie Lin , Yang Zhao , Bingyi Kang , Jiashi Feng , Xihui Liu

Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jeong Hun Yeo , Sangyun Chung , Sungjune Park , Dae Hoe Kim , Jinyoung Moon , Yong Man Ro

Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from long video sequences incurs prohibitive computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Minyoung Park , Taehun Kong , Sangjun Ahn

Applying Multimodal Large Language Models (MLLMs) to video understanding presents significant challenges due to the need to model temporal relations across frames. Existing approaches adopt either implicit temporal modeling, relying solely…

Computer Vision and Pattern Recognition · Computer Science 2025-01-29 Yun Li , Zhe Liu , Yajing Kong , Guangrui Li , Jiyuan Zhang , Chao Bian , Feng Liu , Lina Yao , Zhenbang Sun

Multimodal Large Language Models (MLLMs) have demonstrated significant progress in vision-language tasks, yet they still face challenges when processing long-duration video inputs. The limitation arises from MLLMs' context limit and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Canhui Tang , Zifan Han , Hongbo Sun , Sanping Zhou , Xuchong Zhang , Xin Wei , Ye Yuan , Huayu Zhang , Jinglin Xu , Hao Sun

We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a video to be a 1D sequence of clips, each one associated with its…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 Dotan Kaufman , Gil Levi , Tal Hassner , Lior Wolf

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Seon-Ho Lee , Jue Wang , Zhikang Zhang , David Fan , Xinyu Li

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Letian Kang , Shixian Luo , Yiqiang Li , Yuxin Yin , Shenxuan Zhou , Xiaoyang Yu , Jin Yang , Yong Wu

Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Weiheng Lu , Jian Li , An Yu , Ming-Ching Chang , Shengpeng Ji , Min Xia

The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning…

Sound · Computer Science 2024-06-17 Dongchao Yang , Haohan Guo , Yuanyuan Wang , Rongjie Huang , Xiang Li , Xu Tan , Xixin Wu , Helen Meng

Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics and appearance. Previous methods capture the visual tempo…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Yuanzhong Liu , Junsong Yuan , Zhigang Tu

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

Computation and Language · Computer Science 2025-10-24 Hippolyte Pilchen , Edouard Grave , Patrick Pérez