English
Related papers

Related papers: LiteFrame: Efficient Vision Encoders Unlock Frame …

200 papers

Video analytics are often performed as cloud services in edge settings, mainly to offload computation, and also in situations where the results are not directly consumed at the video sensors. Sending high-quality video data from the edge…

Image and Video Processing · Electrical Eng. & Systems 2023-07-27 Quazi Mishkatul Alam , Israat Haque , Nael Abu-Ghazaleh

The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains. However, this progress is accompanied by a substantial surge in the resource consumption of these models. We…

Computation and Language · Computer Science 2024-12-19 Dingjie Song , Wenjun Wang , Shunian Chen , Xidong Wang , Michael Guan , Benyou Wang

Recent advances in multimodal large language models (MLLMs) have enabled impressive progress in vision-language understanding, yet their high computational cost limits deployment in resource-constrained scenarios such as personal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Quoc-Huy Trinh , Mustapha Abdullahi , Bo Zhao , Debesh Jha

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

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

Long-form video processing fundamentally challenges vision-language models (VLMs) due to the high computational costs of handling extended temporal sequences. Existing token pruning and feature merging methods often sacrifice critical…

Computation and Language · Computer Science 2025-09-11 Chuanqi Cheng , Jian Guan , Wei Wu , Rui Yan

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Qingsong Xie , Zhenyi Liao , Zhijie Deng , Chen chen , Haonan Lu

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yansong Guo , Chaoyang Zhu , Jiayi Ji , Jianghang Lin , Liujuan Cao

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

Machine Learning · Computer Science 2025-02-04 Wilson Yan , Volodymyr Mnih , Aleksandra Faust , Matei Zaharia , Pieter Abbeel , Hao Liu

Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Shuai Zhao , Linchao Zhu , Xiaohan Wang , Yi Yang

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiafei Song , Fengwei Zhou , Jin Qu , Wenjin Jason Li , Tong Wu , Gengjian Xue , Zhikang Zhao , Daomin Wei , Yichao Lu , Bailin Na

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Anni Tang , Tianyu He , Junliang Guo , Xinle Cheng , Li Song , Jiang Bian

Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Yuxuan Wang , Yiqi Song , Cihang Xie , Yang Liu , Zilong Zheng

With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Guo Chen , Yin-Dong Zheng , Jiahao Wang , Jilan Xu , Yifei Huang , Junting Pan , Yi Wang , Yali Wang , Yu Qiao , Tong Lu , Limin Wang

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yi Wang , Haofei Zhang , Qihan Huang , Anda Cao , Gongfan Fang , Wei Wang , Xuan Jin , Jie Song , Mingli Song , Xinchao Wang

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck:…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Zhihao He , Tieyuan Chen , Kangyu Wang , Ziran Qin , Yang Shao , Chaofan Gan , Shijie Li , Zuxuan Wu , Weiyao Lin

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Andreas Blattmann , Robin Rombach , Huan Ling , Tim Dockhorn , Seung Wook Kim , Sanja Fidler , Karsten Kreis

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Shuai Li , Jian Xu , Xiao-Hui Li , Chao Deng , Lin-Lin Huang

The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jihoon Chung , Tyler Zhu , Max Gonzalez Saez-Diez , Juan Carlos Niebles , Honglu Zhou , Olga Russakovsky