English
Related papers

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

200 papers

Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelines therefore either…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Zirui Zhu , Hailun Xu , Yang Luo , Yong Liu , Kanchan Sarkar , Zhenheng Yang , Yang You

Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question. This static approach limits their ability to adaptively…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Haonan Ge , Yiwei Wang , Kai-Wei Chang , Hang Wu , Yujun Cai

Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practical remedy, existing methods still struggle to balance local…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Enwei Tong , Yuanchao Bai , Yao Zhu , Junjun Jiang , Xianming Liu

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Yuke Zhu , Chi Xie , Shuang Liang , Bo Zheng , Sheng Guo

Real-world low-resolution (LR) videos have diverse and complex degradations, imposing great challenges on video super-resolution (VSR) algorithms to reproduce their high-resolution (HR) counterparts with high quality. Recently, the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Xi Yang , Chenhang He , Jianqi Ma , Lei Zhang

Video Multimodal Large Language Models~(Video-MLLM) have achieved remarkable advancements in video understanding tasks. However, constrained by the context length limitation in the underlying LLMs, existing Video-MLLMs typically exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Kuo Wang , Quanlong Zheng , Junlin Xie , Yanhao Zhang , Jinguo Luo , Haonan Lu , Liang Lin , Fan Zhou , Guanbin Li

Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos. Recently, methods were proposed to mine spatiotemporal information via utilizing…

Image and Video Processing · Electrical Eng. & Systems 2021-06-01 Yi Xu , Minyi Zhao , Jing Liu , Xinjian Zhang , Longwen Gao , Shuigeng Zhou , Huyang Sun

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Shaoguang Wang , Weiyu Guo , Ziyang Chen , Yijie Xu , Xuming Hu , Hui Xiong

Referring video object segmentation aims to segment a referent throughout a video sequence according to a natural language expression. It requires aligning the natural language expression with the objects' motions and their dynamic…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Jiajin Tang , Ge Zheng , Sibei Yang

Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectively modeling the temporal dimension (i.e. capturing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Lingyu Kong , Hongzhi Zhang , Jingyuan Zhang , Jianzhao Huang , Kunze Li , Qi Wang , Fuzheng Zhang

As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across frames. Training-free token compression has emerged as a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Minseok Kang , Minhyeok Lee , Jungho Lee , Minjung Kim , Donghyeong Kim , Dayeon Lee , Heeseung Choi , Ig-jae Kim , Sangyoun Lee

Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian…

Image and Video Processing · Electrical Eng. & Systems 2025-10-31 Jiaye Fu , Qiankun Gao , Chengxiang Wen , Yanmin Wu , Siwei Ma , Jiaqi Zhang , Jian Zhang

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Yifan Liu , Chunhua Shen , Changqian Yu , Jingdong Wang

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

The remarkable efficacy of text-to-image diffusion models has motivated extensive exploration of their potential application in video domains. Zero-shot methods seek to extend image diffusion models to videos without necessitating model…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Shuai Yang , Yifan Zhou , Ziwei Liu , Chen Change Loy

Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and…

Computer Vision and Pattern Recognition · Computer Science 2020-05-25 Beibei Jin , Yu Hu , Qiankun Tang , Jingyu Niu , Zhiping Shi , Yinhe Han , Xiaowei Li

Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Thinesh Thiyakesan Ponbagavathi , Constantin Seibold , Alina Roitberg

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Shimin Chen , Yitian Yuan , Shaoxiang Chen , Zequn Jie , Lin Ma

Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Yuqian Yuan , Hang Zhang , Wentong Li , Zesen Cheng , Boqiang Zhang , Long Li , Xin Li , Deli Zhao , Wenqiao Zhang , Yueting Zhuang , Jianke Zhu , Lidong Bing

Video Large Language Models have demonstrated strong video understanding capabilities, yet their practical deployment is hindered by substantial inference costs caused by redundant video tokens. Existing pruning techniques fail to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Leqi Shen , Guoqiang Gong , Tao He , Yifeng Zhang , Pengzhang Liu , Sicheng Zhao , Guiguang Ding