Experts has a new look! Let us know what you think of the updates.

Provide feedback
Home
Scholarly Works
Few-Shot Learning of Video Action Recognition Only...
Conference

Few-Shot Learning of Video Action Recognition Only Based on Video Contents

Abstract

The success of video action recognition based on Deep Neural Networks (DNNs) is highly dependent on a large number of manually labeled videos. In this paper, we introduce a supervised learning approach to recognize video actions with very few training videos. Specifically, we propose Temporal Attention Vectors (TAVs) which adapt various length videos to preserve the temporal information of the entire video. We evaluate the TAVs on UCF101 and …

Authors

Bo Y; Lu Y; He W

Volume

00

Pagination

pp. 584-593

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

March 5, 2020

DOI

10.1109/wacv45572.2020.9093481

Name of conference

2020 IEEE Winter Conference on Applications of Computer Vision (WACV)