.png){kind=icon}
返回
Exploring Rich Semantics for Open-Set Action Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2023.3333206.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Open-set action recognition (OSAR) aims to learn a recognition framework capable of both classifying known classes and identifying unknown actions in open-set scenarios. Existing OSAR methods typically reside in a data-driven paradigm, which ignore the rich semantics in both known and unknown categories. In fact, we humans have the capability of leveraging the captured semantic information, i.e., knowledge and experience, to incisively distinguish samples from known and unknown classes. Motivated by this observation, in this paper, we propose a Unified Semantic Exploration (USE) framework for recognizing actions in open-set scenarios. Specifically, we explore the explicit knowledge semantics by simulating the unknown classes with knowledge-guided virtual classes based on an external knowledge graph, which enables the model to simulate open-set perception during model training. Besides, we propose to learn the implicit data semantics by transferring the knowledge structure of action categories to the visual prototype space for semantic structure preservation. Extensive experiments on several action recognition benchmarks validate the effectiveness of our proposed method.
Keyword:
Semantics
Prototypes
Knowledge graphs
Visualization
Task analysis
Uncertainty
Training
Open-set action recognition
video action recognition
semantic relation modeling
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
分享收藏
分享收藏Grylloptera - a unique origin of the stridulatory fi le in katydids, crickets, and their kin (Archaeorthoptera)Grylloptera-在katydids，，和他们的亲属 (始祖鸟)
OAAI
OAAI分享收藏
查看更多内容