English
Related papers

Related papers: Time-R1: Post-Training Large Vision Language Model…

200 papers

We propose to improve the time-sensitive video understanding (TSV) capability of video large language models (Video-LLMs) with grounded objects (GO). We hypothesize that TSV tasks can benefit from GO within frames, which is supported by our…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Tz-Ying Wu , Sharath Nittur Sridhar , Subarna Tripathi

Video super-resolution (VSR) can achieve better performance compared to single image super-resolution by additionally leveraging temporal information. In particular, the recurrent-based VSR model exploits long-range temporal information…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Xingyu Zhou , Wei Long , Jingbo Lu , Shiyin Jiang , Weiyi You , Haifeng Wu , Shuhang Gu

Large Language Model (LLM)-based agents have shown promise in procedural tasks, but the potential of multimodal instructions augmented by texts and videos to assist users remains under-explored. To address this gap, we propose the Visually…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Muhammet Furkan Ilaslan , Ali Koksal , Kevin Qinhong Lin , Burak Satar , Mike Zheng Shou , Qianli Xu

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Sicheng Yu , Chengkai Jin , Huanyu Wang , Zhenghao Chen , Sheng Jin , Zhongrong Zuo , Xiaolei Xu , Zhenbang Sun , Bingni Zhang , Jiawei Wu , Hao Zhang , Qianru Sun

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…

Large Language Models (LLMs) demonstrate impressive capabilities but lack robust temporal intelligence, struggling to integrate reasoning about the past with predictions and plausible generations of the future. Meanwhile, existing methods…

Computation and Language · Computer Science 2025-06-04 Zijia Liu , Peixuan Han , Haofei Yu , Haoru Li , Jiaxuan You

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language tasks yet remain limited in long video understanding due to the limited context window. Consequently, prevailing approaches tend to rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yang Ding , Yizhen Zhang , Xin Lai , Ruihang Chu , Yujiu Yang

Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Yogesh Kumar

Video-text Large Language Models (video-text LLMs) have shown remarkable performance in answering questions and holding conversations on simple videos. However, they perform almost the same as random on grounding text queries in long and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Yueqian Wang , Xiaojun Meng , Jianxin Liang , Yuxuan Wang , Qun Liu , Dongyan Zhao

Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Yan Shu , Zheng Liu , Peitian Zhang , Minghao Qin , Junjie Zhou , Zhengyang Liang , Tiejun Huang , Bo Zhao

Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Jin-Seop Lee , SungJoon Lee , Jaehan Ahn , YunSeok Choi , Jee-Hyong Lee

Despite the advancements made in Vision Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledge-intensive. Indiscriminately…

Computation and Language · Computer Science 2025-08-26 Zhuo Chen , Xinyu Wang , Yong Jiang , Zhen Zhang , Xinyu Geng , Pengjun Xie , Fei Huang , Kewei Tu

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial…

Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Yuanhao Xiong , Long Zhao , Boqing Gong , Ming-Hsuan Yang , Florian Schroff , Ting Liu , Cho-Jui Hsieh , Liangzhe Yuan

Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Jie Wu , Guanbin Li , Xiaoguang Han , Liang Lin

Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: Moment Retrieval (MR) and Highlight Detection (HD).…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Minseok Kang , Minhyeok Lee , Minjung Kim , Donghyeong Kim , Sangyoun Lee

Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yunzhuo Sun , Xinyue Liu , Yanyang Li , Nanding Wu , Yifang Xu , Linlin Zong , Xianchao Zhang , Wenxin Liang

Referring Video Object Segmentation (RVOS) aims to segment and track objects in videos based on natural language expressions, requiring precise alignment between visual content and textual queries. However, existing methods often suffer…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Seunghun Lee , Jiwan Seo , Jeonghoon Kim , Sungho Moon , Siwon Kim , Haeun Yun , Hyogyeong Jeon , Wonhyeok Choi , Jaehoon Jeong , Zane Durante , Sang Hyun Park , Sunghoon Im

Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…

Machine Learning · Computer Science 2025-07-04 Anurag Arnab , Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

In this work, we tackle the problem of long-form video-language grounding (VLG). Given a long-form video and a natural language query, a model should temporally localize the precise moment that answers the query. Humans can easily solve VLG…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Hyogun Lee , Soyeon Hong , Mujeen Sung , Jinwoo Choi