English
Related papers

Related papers: OTT-Vid: Optimal Transport Temporal Token Compress…

200 papers

Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens and computational inefficiencies. The best token reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Zheng , Jieyu Zhang , Mohammadreza Salehi , Ziqi Gao , Vishnu Iyengar , Norimasa Kobori , Quan Kong , Ranjay Krishna

Reward specification is one of the most tricky problems in Reinforcement Learning, which usually requires tedious hand engineering in practice. One promising approach to tackle this challenge is to adopt existing expert video demonstrations…

Artificial Intelligence · Computer Science 2024-11-05 Yuwei Fu , Haichao Zhang , Di Wu , Wei Xu , Benoit Boulet

Vision-Language Models (VLMs) face significant computational challenges in video processing due to massive data redundancy, which creates prohibitively long token sequences. To address this, we introduce Triage, a training-free,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Anmin Wang , Nan Zhang , Wei Tao , Xiaoyang Qu , Guokuan Li , Jiguang Wan , Jianzong Wang

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Ruyang Liu , Chen Li , Haoran Tang , Yixiao Ge , Ying Shan , Ge Li

We address the task of supervised action segmentation which aims to partition a video into non-overlapping segments, each representing a different action. Recent works apply transformers to perform temporal modeling at the frame-level,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Zijia Lu , Ehsan Elhamifar

"Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency often correlates with improved model performance…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Xin Jin , Jinming Liu , Yuntao Wei , Junyan Lin , Zhicheng Wang , Jianguo Huang , Xudong Yang , Yanxiao Liu , Wenjun Zeng

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Yaozong Zheng , Bineng Zhong , Qihua Liang , Zhiyi Mo , Shengping Zhang , Xianxian Li

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Yiyang Huang , Yizhou Wang , Yun Fu

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyu Lu , Feng Zhang , Wenwei Jin , Huanling Hu , Tianjun Shi , Shikai Jiang , Yao Hu , Jiawei Li

Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Sijie Li , Biao Qian , Jungong Han

The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we…

Computation and Language · Computer Science 2021-11-29 Jingjing Xu , Hao Zhou , Chun Gan , Zaixiang Zheng , Lei Li

Recent achievements of vision-language models in end-to-end OCR point to a new avenue for low-loss compression of textual information. This motivates earlier works that render the Transformer's input into images for prefilling, which…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Dian Jiao , Jiaxin Duan , Shuai Zhao , Jiabing Leng , Yiran Zhang , Feng Huang

Video Temporal Grounding (VTG) aims to localize the video segment that corresponds to a natural language query, which requires a comprehensive understanding of complex temporal dynamics. Existing Vision-LMMs typically perceive temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chaohong Guo , Yihan He , Yongwei Nie , Fei Ma , Xuemiao Xu , Chengjiang Long

Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning offers significant savings, but existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Patrick Glandorf , Thomas Norrenbrock , Bodo Rosenhahn

Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yigui Feng , Qinglin Wang , Yang Liu , Jie Liu

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Ziyao Wang , Chen Chen , Jingtao Li , Weiming Zhuang , Jiabo Huang , Ang Li , Lingjuan Lyu

In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too much unnecessary computation. Pruning redundant vision tokens for high VLM inference efficiency has…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Guangyuan Li , Rongzhen Zhao , Jinhong Deng , Yanbo Wang , Joni Pajarinen

We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Michael S. Ryoo , Honglu Zhou , Shrikant Kendre , Can Qin , Le Xue , Manli Shu , Jongwoo Park , Kanchana Ranasinghe , Silvio Savarese , Ran Xu , Caiming Xiong , Juan Carlos Niebles

The relevance of optimal transport methods to machine learning has long been hindered by two salient limitations. First, the $O(n^3)$ computational cost of standard sample-based solvers (when used on batches of $n$ samples) is prohibitive.…

Machine Learning · Computer Science 2023-06-01 Meyer Scetbon , Michal Klein , Giovanni Palla , Marco Cuturi

We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Georg Heigold , Matthias Minderer , Alexey Gritsenko , Alex Bewley , Daniel Keysers , Mario Lučić , Fisher Yu , Thomas Kipf