.png){kind=icon}
返回
Weakly-supervised action localization via embedding-modeling iterative optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.107831.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Action recognition and localization in untrimmed videos in weakly supervised scenario is a challenging problem of great application prospects. Limited by the information available in video-level labels, it is a promising attempt to fully leverage the instructive knowledge learned on trimmed videos to facilitate analysis of untrimmed videos, considering that there are abundant trimmed videos which are publicly available and well segmented with semantic descriptions. In order to enforce effective trimmed untrimmed augmentation, this paper presents a novel framework of embedding-modeling iterative optimization network, referred to as IONet. In the proposed method, action classification modeling and shared subspace embedding are learned jointly in an iterative way, so that robust cross-domain knowledge transfer is achieved. With a carefully designed two-stage self-attentive representation learning workflow for untrimmed videos, irrelevant backgrounds are eliminated and fine-grained temporal relevance can be robustly explored. Extensive experiments are conducted on two benchmark datasets, i.e., THUMOS14 and ActivityNet1.3, and experimental results clearly corroborate the efficacy of our method. Source code is available on GitHub.
Keyword:
Action recognition
Temporal action localization
Attention mechanism
Generative adversarial networks
Subspace embedding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Learning motion representation for real-time spatio-temporal action localization实时时空动作定位的运动表示学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Social network model for crowd anomaly detection and localization面向人群异常检测与定位的社交网络模型PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏Motion analysis: Action detection, recognition and evaluation based on motion capture dataPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Generative adversarial framework for depth filling via Wasserstein metric, cosine transform and domain transferPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容