Open AccessDeep ChaosNet for Action Recognition in Videos
Author(s) -
Huafeng Chen,
Maosheng Zhang,
Zheng-Ming Gao,
Yunhong Zhao
Publication year - 2021
Publication title -
complexity
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.447
H-Index - 61
eISSN - 1099-0526
pISSN - 1076-2787
DOI - 10.1155/2021/6634156
Subject(s) - computer science , action recognition , artificial intelligence , encoder , pattern recognition (psychology) , segmentation , coding (social sciences) , feature (linguistics) , action (physics) , deep neural networks , artificial neural network , mathematics , linguistics , statistics , philosophy , physics , quantum mechanics , class (philosophy) , operating system
Current methods of chaos-based action recognition in videos are limited to the artificial feature causing the low recognition accuracy. In this paper, we improve ChaosNet to the deep neural network and apply it to action recognition. First, we extend ChaosNet to deep ChaosNet for extracting action features. Then, we send the features to the low-level LSTM encoder and high-level LSTM encoder for obtaining low-level coding output and high-level coding results, respectively. The agent is a behavior recognizer for producing recognition results. The manager is a hidden layer, responsible for giving behavioral segmentation targets at the high level. Our experiments are executed on two standard action datasets: UCF101 and HMDB51. The experimental results show that the proposed algorithm outperforms the state of the art.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom