paper-with-me

Papers

WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos

2020-06-05 · CVPR 2021 1 · Mingfei Gao, Yingbo Zhou, ran Xu, Richard Socher, Caiming Xiong

Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious annotations of temporal action boundaries for training, which hinders the scalability of online action detection systems. We propose WOAD, a weakly supervised framework that can be trained using only video-class labels. WOAD contains two jointly-trained modules, i.e., temporal proposal generator (TPG) and online action recognizer (OAR). Supervised by video-class labels, TPG works offline and targets at accurately mining pseudo frame-level labels for OAR. With the supervisory signals from TPG, OAR learns to conduct action detection in an online fashion. Experimental results on THUMOS'14, ActivityNet1.2 and ActivityNet1.3 show that our weakly-supervised method largely outperforms weakly-supervised baselines and achieves comparable performance to the previous strongly-supervised methods. Beyond that, WOAD is flexible to leverage strong supervision when it is available. When strongly supervised, our method obtains the state-of-the-art results in the tasks of both online per-frame action recognition and online detection of action start.

📄 PDF Abstract BibTeX arXiv:2006.03732

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionAction RecognitionOnline Action Detection

Similar Papers 제목 키워드 기반

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

2025-01-19 · Quan Zhang, Yuxin Qi, Xi Tang, Rui Yuan 외

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training…

Action LocalizationDenoisingPseudo LabelTemporal Action Localization+1

Multiple Instance Detection Network with Online Instance Classifier Refinement

2017-04-01 · CVPR 2017 7 · Peng Tang, Xinggang Wang, Xiang Bai, Wenyu Liu

Of late, weakly supervised object detection is with great importance in object recognition. Based on deep learning, weakly supervised detectors have achieved many promising results. However, compared with fully supervise…

Multiple Instance LearningObjectobject-detectionObject Detection+2

Weakly Supervised Online Action Detection for Infant General Movements

2022-08-07 · Tongyi Luo, Jia Xiao, Chuncao Zhang, Siheng Chen 외

To make the earlier medical intervention of infants' cerebral palsy (CP), early diagnosis of brain damage is critical. Although general movements assessment(GMA) has shown promising results in early CP detection, it is l…

Action DetectionClassificationOnline Action Detection

Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes

2022-04-01 · Akhil Meethal, Marco Pedersoli, Zhongwen Zhu, Francisco Perdigon Romero 외

Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models. St…

Data Augmentationobject-detectionObject DetectionWeakly-supervised Learning+1

Generative Adversarial Learning Towards Fast Weakly Supervised Detection

2018-06-01 · CVPR 2018 6 · Yunhan Shen, Rongrong Ji, Shengchuan Zhang, WangMeng Zuo 외

Weakly supervised object detection has attracted extensive research efforts in recent years. Without the need of annotating bounding boxes, the existing methods usually follow a two/multi-stage pipeline with an online co…

Objectobject-detectionObject DetectionWeakly Supervised Object Detection