Joint Learning On The Hierarchy Representation for Fine-Grained Human Action Recognition
| Autor: | Liyuan Li, Feng Lin, Hui Li Tan, Joo-Hwee Lim, Mei Chee Leong, Haosong Zhang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Exploit Hierarchy (mathematics) business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Representation (systemics) Computer Science - Computer Vision and Pattern Recognition Frame rate Encoding (memory) Feature (machine learning) Artificial intelligence Element (category theory) business Joint (audio engineering) |
| Popis: | Fine-grained human action recognition is a core research topic in computer vision. Inspired by the recently proposed hierarchy representation of fine-grained actions in FineGym and SlowFast network for action recognition, we propose a novel multi-task network which exploits the FineGym hierarchy representation to achieve effective joint learning and prediction for fine-grained human action recognition. The multi-task network consists of three pathways of SlowOnly networks with gradually increased frame rates for events, sets and elements of fine-grained actions, followed by our proposed integration layers for joint learning and prediction. It is a two-stage approach, where it first learns deep feature representation at each hierarchical level, and is followed by feature encoding and fusion for multi-task learning. Our empirical results on the FineGym dataset achieve a new state-of-the-art performance, with 91.80% Top-1 accuracy and 88.46% mean accuracy for element actions, which are 3.40% and 7.26% higher than the previous best results. Camera ready for IEEE ICIP 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|