arrow
返回

Content Temporal Relation Network for temporal action proposal generation

delete2024-05-01
delete0
PRE
AI
G
Gan, Ming-Gang
Y
Yan Zhang *
DOI:10.1016/j.patcog.2023.110245delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Temporal action proposal generation is an essential step for untrimmed video analysis and gains much attention from academia. However, most of the prior works predict the confidence score of each proposal separately and neglect the relations between proposals, limiting their performance. In this work, we design a novel Content Temporal Relation Network (CTRNet) to generate temporal action proposals by exploring the content and temporal semantic relations between proposals simultaneously. Specifically, we design a proposal feature map generation layer to convert the temporal semantic relations of proposals into spatial relations. Based on the proposal feature map, we propose a content-temporal relation module, which applies a novel adaptive -dilated convolution to model the temporal semantic relations between proposals and designs a content-adaptive convolution operation to explore the content semantic relation between proposals. Considering the temporal and content semantic relations between proposals, CTRNet has learned discriminative proposal features to improve performance. Extensive experiments are performed on two mainstream temporal action detection datasets, and CTRNet significantly outperforms the previous state-of-the-art methods. The codes are available at https://github.com/YanZhang-bit/CTRNet.
Keyword:
Temporal action proposal generation
Temporal action detection
Untrimmed video analysis
Proposal-proposal relations

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

B
beijing institute of technology
学者数:
5.5W
论文数: 4.0W
被引数: 63
引用论文

引用论文

Video representation learning for temporal action detection using global-local attention
err2023-02-01
err2
PREAI
errTang, Yiping; Zheng, Yang; Wei, Chen; Guo, Kaitai; Hu, Haihong; Liang, Jimin
err分享
err收藏
Climate policy: Steps to China's carbon peak气候政策: 迈向中国碳峰值的步骤
err2015-06-17
err0
errOAAI
errZhu Liu; Dabo Guan; Scott Moore; Henry Lee; Jun Su; Qiang Zhang
err分享
err收藏
Play and rewind: Context-aware video temporal action proposals
err2020-11-01
err19
PREAI
errGao, Lianli; Li, Tao; Song, Jingkuan; Zhao, Zhou; Shen, Heng Tao
err分享
err收藏
err分享
err收藏
学者 查看更多内容