中文
相关论文

相关论文: Temporal Localization of Fine-Grained Actions in V…

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Fengshun Wang , Qiurui Wang , Yuting Wang

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Rui Su , Dong Xu , Luping Zhou , Wanli Ouyang

Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…

计算机视觉与模式识别 · 计算机科学 2022-04-26 Junfei Xiao , Longlong Jing , Lin Zhang , Ju He , Qi She , Zongwei Zhou , Alan Yuille , Yingwei Li

Understanding human behavior and activity facilitates advancement of numerous real-world applications, and is critical for video analysis. Despite the progress of action recognition algorithms in trimmed videos, the majority of real-world…

计算机视觉与模式识别 · 计算机科学 2021-10-04 Elahe Vahdani , Yingli Tian

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

计算机视觉与模式识别 · 计算机科学 2020-04-01 Mohsen Fayyaz , Juergen Gall

Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Tunc Alkanat , Erkut Akdag , Egor Bondarev , Peter H. N. De With

Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have…

计算机视觉与模式识别 · 计算机科学 2018-12-18 Sujoy Paul , Sourya Roy , Amit K Roy-Chowdhury

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…

计算机视觉与模式识别 · 计算机科学 2023-09-27 Guiqin Wang , Peng Zhao , Cong Zhao , Shusen Yang , Jie Cheng , Luziwei Leng , Jianxing Liao , Qinghai Guo

The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and label action boundaries to create annotations for training…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Anna Kukleva , Hilde Kuehne , Fadime Sener , Juergen Gall

Weakly supervised temporal action localization aims to localize temporal boundaries of actions and simultaneously identify their categories with only video-level category labels. Many existing methods seek to generate pseudo labels for…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Linjiang Huang , Liang Wang , Hongsheng Li

Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary annotations. Weakly supervised methods with cheaper…

计算机视觉与模式识别 · 计算机科学 2020-07-06 Xinpeng Ding , Nannan Wang , Xinbo Gao , Jie Li , Xiaoyu Wang , Tongliang Liu

This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…

计算机视觉与模式识别 · 计算机科学 2017-04-05 Yi Zhu , Shawn Newsam

When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from…

计算机视觉与模式识别 · 计算机科学 2019-08-14 Jungbeom Lee , Eunji Kim , Sungmin Lee , Jangho Lee , Sungroh Yoon

The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive and effective algorithm that localizes actions from their class…

计算机视觉与模式识别 · 计算机科学 2017-12-14 Pascal Mettes , Cees G. M. Snoek , Shih-Fu Chang

Temporal action localization in untrimmed videos is an important but difficult task. Difficulties are encountered in the application of existing methods when modeling temporal structures of videos. In the present study, we developed a novel…

计算机视觉与模式识别 · 计算机科学 2019-11-05 Yuan Zhou , Hongru Li , Sun-Yuan Kung

We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the…

计算机视觉与模式识别 · 计算机科学 2018-01-09 Seunghoon Hong , Donghun Yeo , Suha Kwak , Honglak Lee , Bohyung Han

We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails to learn action completeness, resulting in fragmentary…

计算机视觉与模式识别 · 计算机科学 2021-08-12 Pilhyeon Lee , Hyeran Byun

We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other…

计算机视觉与模式识别 · 计算机科学 2016-04-25 Zheng Shou , Dongang Wang , Shih-Fu Chang

Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos…

计算机视觉与模式识别 · 计算机科学 2020-11-10 Alejandro Pardo , Humam Alwassel , Fabian Caba Heilbron , Ali Thabet , Bernard Ghanem

Action localization in untrimmed videos is an important topic in the field of video understanding. However, existing action localization methods are restricted to a pre-defined set of actions and cannot localize unseen activities. Thus, we…

计算机视觉与模式识别 · 计算机科学 2019-07-01 Zhu Zhang , Zhou Zhao , Zhijie Lin , Jingkuan Song , Deng Cai