Current Result Document : 795 / 795
| 한글제목(Korean Title) |
FTSnet: 동작 인식을 위한 간단한 합성곱 신경망 |
| 영문제목(English Title) |
FTSnet: A Simple Convolutional Neural Networks for Action Recognition |
| 저자(Author) |
조옥란
이효종
Yulan Zhao
Hyo Jong Lee
|
| 원문수록처(Citation) |
VOL 28 NO. 02 PP. 0878 ~ 0879 (2021. 11) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance. |
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
