English
Related papers

Related papers: Video-Specific Query-Key Attention Modeling for We…

200 papers

This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Shubham Trehan , Sathyanarayanan N. Aakur

Action localization networks are often structured as a feature encoder sub-network and a localization sub-network, where the feature encoder learns to transform an input video to features that are useful for the localization sub-network to…

Computer Vision and Pattern Recognition · Computer Science 2021-09-07 Deepak Sridhar , Niamul Quader , Srikanth Muralidharan , Yaoxin Li , Peng Dai , Juwei Lu

Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Minuk Ma , Sunjae Yoon , Junyeong Kim , Youngjoon Lee , Sunghun Kang , Chang D. Yoo

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Yijun Song , Jingwen Wang , Lin Ma , Zhou Yu , Jun Yu

This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track. Temporal Action Localization (TAL)…

Computer Vision and Pattern Recognition · Computer Science 2021-07-28 Haisheng Su , Peiqin Zhuang , Yukun Li , Dongliang Wang , Weihao Gan , Wei Wu , Yu Qiao

Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Yongfei Liu , Bo Wan , Lin Ma , Xuming He

This paper strives for spatio-temporal localization of human actions in videos. In the literature, the consensus is to achieve localization by training on bounding box annotations provided for each frame of each training video. As…

Computer Vision and Pattern Recognition · Computer Science 2018-10-02 Pascal Mettes , Cees G. M. Snoek

The present few-shot temporal action localization model can't handle the situation where videos contain multiple action instances. So the purpose of this paper is to achieve manifold action instances localization in a lengthy untrimmed…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Fengshun Wang , Qiurui Wang , Yuting Wang

This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of…

Computer Vision and Pattern Recognition · Computer Science 2018-06-29 Guilhem Chéron , Anton Osokin , Ivan Laptev , Cordelia Schmid

Training deep learning based video classifiers for action recognition requires a large amount of labeled videos. The labeling process is labor-intensive and time-consuming. On the other hand, large amount of weakly-labeled images are…

Computer Vision and Pattern Recognition · Computer Science 2017-08-04 Junnan Li , Yongkang Wong , Qi Zhao , Mohan Kankanhalli

Video action detection requires dense spatio-temporal annotations, which are both challenging and expensive to obtain. However, real-world videos often vary in difficulty and may not require the same level of annotation. This paper analyzes…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Aayush Rana , Akash Kumar , Vibhav Vineet , Yogesh S Rawat

In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video. Specifically, given an untrimmed video and a query sentence, our goal is to localize a temporal segment in the video that semantically…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Zhenfang Chen , Lin Ma , Wenhan Luo , Peng Tang , Kwan-Yee K. Wong

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive…

Computer Vision and Pattern Recognition · Computer Science 2018-04-23 Yu-Wei Chao , Sudheendra Vijayanarasimhan , Bryan Seybold , David A. Ross , Jia Deng , Rahul Sukthankar

In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work takes on the novel task of action highlighting, which…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Seito Kasai , Yuchi Ishikawa , Masaki Hayashi , Yoshimitsu Aoki , Kensho Hara , Hirokatsu Kataoka

The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Chen Zhang , Guorong Li , Yuankai Qi , Hanhua Ye , Laiyun Qing , Ming-Hsuan Yang , Qingming Huang

In this paper we introduce the problem of Visual Semantic Role Labeling: given an image we want to detect people doing actions and localize the objects of interaction. Classical approaches to action recognition either study the task of…

Computer Vision and Pattern Recognition · Computer Science 2015-05-19 Saurabh Gupta , Jitendra Malik

Spatio-temporal action detection in videos is typically addressed in a fully-supervised setup with manual annotation of training videos required at every frame. Since such annotation is extremely tedious and prohibits scalability, there is…

Computer Vision and Pattern Recognition · Computer Science 2018-11-29 Guilhem Chéron , Jean-Baptiste Alayrac , Ivan Laptev , Cordelia Schmid

The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Guodong Ding , Angela Yao

In this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos. While recent approaches combine representation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Federico Spurio , Emad Bahrami , Gianpiero Francesca , Juergen Gall

We present the submission of Samsung AI Centre Cambridge to the CVPR2020 EPIC-Kitchens Action Recognition Challenge. In this challenge, action recognition is posed as the problem of simultaneously predicting a single `verb' and `noun' class…

Computer Vision and Pattern Recognition · Computer Science 2020-07-07 Juan-Manuel Perez-Rua , Antoine Toisoul , Brais Martinez , Victor Escorcia , Li Zhang , Xiatian Zhu , Tao Xiang