Weakly-Supervised Temporal Action Localization by Background Suppression

被引:0
作者
Liu, Mengxue [1 ]
Gao, Xiangjun [1 ]
Ge, Fangzhen [1 ]
Liu, Huaiyu [1 ]
Li, Wenjing [1 ]
机构
[1] Huaibei Normal Univ, Sch Comp Sci & Technol, Huaibei 235000, Peoples R China
来源
2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC) | 2021年
关键词
Weak Supervision; Temporal Action Localization; Filtering Module; Background Suppression;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a novel method of background suppression to solve the issue that background regions are recognized as actions in weakly-supervised temporal action localization. The general attention-based action localization methods tend to use the attention module to generate segment-level attention weights. But there is little difference between the attentions from the background segments similar to the target actions and the attentions of the action segments, which causes the result that many background segments related to the target actions are still recognized as actions. To address this issue, a weakly-supervised temporal action localization network by background suppression (BS-WTAL) is designed. It introduces a filtering module for suppressing the background features and encouraging the action features, a classification module for identifying action categories and a generative attention module for segment-wise representation modeling. This enables BS-WTAL to suppress background to improve localization performance. Furthermore, we conduct ablation studies from different perspectives. Extensive experiments were performed on two datasets - THUMOS14 and ActivityNet1.2. Our approach shows better performance on these two datasets, even comparable with state-of-the-art fully-supervised methods.
引用
收藏
页码:7074 / 7081
页数:8
相关论文
共 50 条
[41]   Weakly-Supervised Temporal Action Localization with Multi-Head Cross-Modal Attention [J].
Ren, Hao ;
Ren, Haoran ;
Ran, Wu ;
Lu, Hong ;
Jin, Cheng .
PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT III, 2022, 13631 :281-295
[42]   Video Complicated-Information Extraction and Filtering Network for Weakly-Supervised Temporal Action Localization [J].
Li, Jiaxuan ;
Ma, Tiancheng ;
Yang, Xiaohui ;
Yang, Lijun ;
Zheng, Chen .
IEEE SIGNAL PROCESSING LETTERS, 2025, 32 :2334-2338
[43]   Weakly supervised temporal action localization: a survey [J].
Li, Ronglu ;
Zhang, Tianyi ;
Zhang, Rubo .
MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (32) :78361-78386
[44]   Temporal Dropout for Weakly Supervised Action Localization [J].
Xie, Chi ;
Zhuang, Zikun ;
Zhao, Shengjie ;
Liang, Shuang .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (03)
[45]   Action Shuffling for Weakly Supervised Temporal Localization [J].
Zhang, Xiao-Yu ;
Shi, Haichao ;
Li, Changsheng ;
Shi, Xinchu .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :4447-4457
[46]   Enhancing action discrimination via category-specific frame clustering for weakly-supervised temporal action localization [J].
Xia, Huifen ;
Zhan, Yongzhao ;
Liu, Honglin ;
Ren, Xiaopeng .
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2024, 25 (06) :809-823
[47]   Weakly supervised temporal action localization with actionness-guided false positive suppression [J].
Li, Zhilin ;
Wang, Zilei ;
Liu, Qinying .
NEURAL NETWORKS, 2024, 175
[48]   PFWNet: Pretraining neural network via feature jigsaw puzzle for weakly-supervised temporal action localization [J].
Wang, Binglu ;
Zhao, Yongqiang ;
Zhang, Yani .
NEUROCOMPUTING, 2021, 443 :162-173
[49]   ACTION COHERENCE NETWORK FOR WEAKLY SUPERVISED TEMPORAL ACTION LOCALIZATION [J].
Zhai, Yuanhao ;
Wang, Le ;
Liu, Ziyi ;
Zhang, Qilin ;
Hua, Gang ;
Zheng, Nanning .
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, :3696-3700
[50]   Weakly Supervised Temporal Action Localization with Segment-Level Labels [J].
Ding, Xinpeng ;
Wang, Nannan ;
Li, Jie ;
Gao, Xinbo .
PATTERN RECOGNITION AND COMPUTER VISION, PT I, 2021, 13019 :42-54