English
Related papers

Related papers: HaltingVT: Adaptive Token Halting Transformer for …

200 papers

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , Cho-Jui Hsieh

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Mattia Soldan , Fabian Caba Heilbron , Bernard Ghanem , Josef Sivic , Bryan Russell

Video tokenization procedure is critical for a wide range of video processing tasks. Most existing approaches directly transform video into fixed-grid and patch-wise tokens, which exhibit limited versatility. Spatially, uniformly allocating…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Zhenghao Chen , Zicong Chen , Lei Liu , Yiming Wu , Dong Xu

Whether by processing videos with fixed resolution from start to end or incorporating pooling and down-scaling strategies, existing video transformers process the whole video content throughout the network without specially handling the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Chenbin Pan , Rui Hou , Hanchao Yu , Qifan Wang , Senem Velipasalar , Madian Khabsa

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Haozhe Qi , Kevin Qu , Mahdi Rad , Rui Wang , Alexander Mathis , Marc Pollefeys

This paper tackles the problem of efficient video recognition. In this area, video transformers have recently dominated the efficiency (top-1 accuracy vs FLOPs) spectrum. At the same time, there have been some attempts in the image domain…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Wele Gedara Chaminda Bandara , Vishal M. Patel

Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is especially pronounced in video compression, where frame-wise…

Image and Video Processing · Electrical Eng. & Systems 2025-10-14 Zongyu Guo , Zhaoyang Jia , Jiahao Li , Xiaoyi Zhang , Bin Li , Yan Lu

Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from heavy computational costs induced by the massive number…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Joonmyung Choi , Sanghyeok Lee , Jaewon Chu , Minhyuk Choi , Hyunwoo J. Kim

Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the relationship among them. However, many of these tokens are…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Foozhan Ataiefard , Walid Ahmed , Habib Hajimolahoseini , Saina Asani , Farnoosh Javadi , Mohammad Hassanpour , Omar Mohamed Awad , Austin Wen , Kangling Liu , Yang Liu

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Shoufa Chen , Chongjian Ge , Zhan Tong , Jiangliu Wang , Yibing Song , Jue Wang , Ping Luo

For the last few decades, the application of signal-adaptive transform coding to video compression has been stymied by the large computational complexity of matrix-based solutions. In this paper, we propose a novel parametric approach to…

Image and Video Processing · Electrical Eng. & Systems 2025-05-29 Amir Said , Xin Zhao , Marta Karczewicz , Hilmi E. Egilmez , Vadim Seregin , Jianle Chen

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Mingbao Lin , Mengzhao Chen , Yuxin Zhang , Chunhua Shen , Rongrong Ji , Liujuan Cao

Transformers have become one of the dominant architectures in the field of computer vision. However, there are yet several challenges when applying such architectures to video data. Most notably, these models struggle to model the temporal…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Gabriele Prato , Yale Song , Janarthanan Rajendran , R Devon Hjelm , Neel Joshi , Sarath Chandar

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Quanfu Fan , Chun-Fu Chen , Hilde Kuehne , Marco Pistoia , David Cox

In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Boyu Chen , Peixia Li , Baopu Li , Chuming Li , Lei Bai , Chen Lin , Ming Sun , Junjie Yan , Wanli Ouyang

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Zheng , Jieyu Zhang , Jianing Zhang , Weikai Huang , Ashutosh Kumar , Quan Kong , Oncel Tuzel , Chun-Liang Li , Ranjay Krishna

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xue Li , Xiaonan Song , Henry Hu

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Yuang Liu , Qiang Zhou , Jing Wang , Fan Wang , Jun Wang , Wei Zhang

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Sina Hajimiri , Farzad Beizaee , Fereshteh Shakeri , Christian Desrosiers , Ismail Ben Ayed , Jose Dolz