English
Related papers

Related papers: An Efficient Spatio-Temporal Pyramid Transformer f…

200 papers

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Image and Video Processing · Electrical Eng. & Systems 2023-03-21 Xiangyu Chen , Xintao Wang , Jiantao Zhou , Yu Qiao , Chao Dong

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Gedas Bertasius , Lorenzo Torresani , Jianbo Shi

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate performance degradation caused by domain-shift. Most of…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Congcong Li , Dawei Du , Libo Zhang , Longyin Wen , Tiejian Luo , Yanjun Wu , Pengfei Zhu

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Yilin Wen , Hao Pan , Lei Yang , Jia Pan , Taku Komura , Wenping Wang

Spatial-temporal action detection is a vital part of video understanding. Current spatial-temporal action detection methods mostly use an object detector to obtain person candidates and classify these person candidates into different action…

Computer Vision and Pattern Recognition · Computer Science 2022-10-28 Lin Sui , Chen-Lin Zhang , Lixin Gu , Feng Han

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

We address the challenging task of human reaction generation, which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Baptiste Chopin , Hao Tang , Naima Otberdout , Mohamed Daoudi , Nicu Sebe

Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length),…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yu Kiu , Lau , Chao Chen , Ge Jin , Chen Feng

Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Le Yang , Junwei Han , Tao Zhao , Nian Liu , Dingwen Zhang

Short-Term object-interaction Anticipation consists of detecting the location of the next-active objects, the noun and verb categories of the interaction, and the time to contact from the observation of egocentric video. This ability is…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Lorenzo Mur-Labadia , Ruben Martinez-Cantin , Josechu Guerrero , Giovanni Maria Farinella , Antonino Furnari

Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph Attention Network (STGAtt). By leveraging a unified graph…

Machine Learning · Computer Science 2025-08-26 Zhuding Liang , Jianxun Cui , Qingshuang Zeng , Feng Liu , Nenad Filipovic , Tijana Geroski

Currently, in the field of video-text retrieval, there are many transformer-based methods. Most of them usually stack frame features and regrade frames as tokens, then use transformers for video temporal modeling. However, they commonly…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Ni Wang , Dongliang Liao , Xing Xu

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir

Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short- and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Zhanzhong Pang , Fadime Sener , Angela Yao

Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource…

Computer Vision and Pattern Recognition · Computer Science 2022-08-04 Edward Fish , Jon Weinbren , Andrew Gilbert

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

Computer Vision and Pattern Recognition · Computer Science 2020-01-20 Anoop Cherian , Jue Wang , Chiori Hori , Tim K. Marks

We present a method to accelerate global illumination computation in dynamic environments by taking advantage of limitations of the human visual system. A model of visual attention is used to locate regions of interest in a scene and to…

Graphics · Computer Science 2007-05-23 Yang Li Hector Yee

Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Shuming Liu , Mengmeng Xu , Chen Zhao , Xu Zhao , Bernard Ghanem

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Lei Chen , Zhan Tong , Yibing Song , Gangshan Wu , Limin Wang

Accurate behavior prediction for vehicles is essential but challenging for autonomous driving. Most existing studies show satisfying performance under regular scenarios, but most neglected safety-critical scenarios. In this study, a…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Dongyang Xu , Yiran Luo , Tianle Lu , Qingfan Wang , Qing Zhou , Bingbing Nie