ACTION RECOGNITION: FIRST-AND SECOND-ORDER 3D FEATURE IN BI-DIRECTIONAL ATTENTION NETWORK

Citations

WEB OF SCIENCE

0
Citations

SCOPUS

1

초록

This paper considers a 3D convolutional neural network (CNN) that learns spatial and temporal regions of higher importance through a bi-direction long short-term memory (bi-LSTM) attention for action recognition. First- and second-order differences of spatially most relevant C3D features (sp-m-C3D) are obtained, and the concatenation of the two differences with the sp-m-C3D is used to generate a temporal attention on the sp-m-C3D using a bi-LSTM. Temporally most relevant sp-m-C3D features are fed into another bi-LSTM for action recognition. Essentially, the network learns spatial and temporal regions of high importance for action recognition. We evaluate the network on two public action recognition datasets: UCF-101 (YouTube Action) and HMDB51. The proposed network performs better compared to other state-of-the-art networks.

키워드

C3D; bi-directional LSTM; Attention; spatio-temporal bi-directional LSTM Attention; Attention; Bi-directional LSTM; C3D; Spatio-temporal bi-directional LSTM Attention
제목
ACTION RECOGNITION: FIRST-AND SECOND-ORDER 3D FEATURE IN BI-DIRECTIONAL ATTENTION NETWORK
저자
Kwon, Oh Chul; Kim, Junyeong; Yoo, Chang D.
DOI
10.1109/ICIP.2018.8451493
발행일
2018-10
유형
Proceedings Paper
저널명
2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
페이지
3453 ~ 3457