English
Related papers

Related papers: Is Space-Time Attention All You Need for Video Und…

200 papers

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Kunchang Li , Yali Wang , Junhao Zhang , Peng Gao , Guanglu Song , Yu Liu , Hongsheng Li , Yu Qiao

Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yushi Huang , Xingtong Ge , Ruihao Gong , Chengtao Lv , Jun Zhang

Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks,…

Computer Vision and Pattern Recognition · Computer Science 2021-11-03 Manjin Kim , Heeseung Kwon , Chunyu Wang , Suha Kwak , Minsu Cho

Video Captioning and Summarization have become very popular in the recent years due to advancements in Sequence Modelling, with the resurgence of Long-Short Term Memory networks (LSTMs) and introduction of Gated Recurrent Units (GRUs).…

Computer Vision and Pattern Recognition · Computer Science 2019-06-10 Manjot Bilkhu , Siyang Wang , Tushar Dobhal

Video classification is highly important with wide applications, such as video search and intelligent surveillance. Video naturally consists of static and motion information, which can be represented by frame and optical flow. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2017-11-10 Yuxin Peng , Yunzhen Zhao , Junchao Zhang

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Rajat Koner , Tanveer Hannan , Suprosanna Shit , Sahand Sharifzadeh , Matthias Schubert , Thomas Seidl , Volker Tresp

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Reza Azad , René Arimond , Ehsan Khodapanah Aghdam , Amirhossein Kazerouni , Dorit Merhof

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Qirui Li , Guangcong Zheng , Qi Zhao , Jie Li , Bin Dong , Yiwu Yao , Xi Li

We introduce a new attention mechanism, dubbed structural self-attention (StructSA), that leverages rich correlation patterns naturally emerging in key-query interactions of attention. StructSA generates attention maps by recognizing…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Manjin Kim , Paul Hongsuck Seo , Cordelia Schmid , Minsu Cho

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Dongho Lee , Jongseo Lee , Jinwoo Choi

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges for explainability, a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Zerui Wang , Yan Liu

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Minh Khoa Le , Kien Do , Duc Thanh Nguyen , Truyen Tran

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Shahla John

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Dongliang He , Zhichao Zhou , Chuang Gan , Fu Li , Xiao Liu , Yandong Li , Limin Wang , Shilei Wen

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Chao Li , Qiaoyong Zhong , Di Xie , Shiliang Pu

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

In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new Transformer block, a fully autoregressive video future…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Xi Ye , Guillaume-Alexandre Bilodeau

The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Pritam Mishra , Coloma Ballester , Dimosthenis Karatzas