Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition

  • Yiyi Zhang Shanghai Jiao Tong University
  • Li Niu Shanghai Jiao Tong University
  • Ziqi Pan Shanghai Jiao Tong University
  • Meichao Luo Shanghai Jiao Tong University
  • Jianfu Zhang Shanghai Jiao Tong University
  • Dawei Cheng Shanghai Jiao Tong University
  • Liqing Zhang Shanghai Jiao Tong University

Abstract

Static image action recognition, which aims to recognize action based on a single image, usually relies on expensive human labeling effort such as adequate labeled action images and large-scale labeled image dataset. In contrast, abundant unlabeled videos can be economically obtained. Therefore, several works have explored using unlabeled videos to facilitate image action recognition, which can be categorized into the following two groups: (a) enhance visual representations of action images with a designed proxy task on unlabeled videos, which falls into the scope of self-supervised learning; (b) generate auxiliary representations for action images with the generator learned from unlabeled videos. In this paper, we integrate the above two strategies in a unified framework, which consists of Visual Representation Enhancement (VRE) module and Motion Representation Augmentation (MRA) module. Specifically, the VRE module includes a proxy task which imposes pseudo motion label constraint and temporal coherence constraint on unlabeled videos, while the MRA module could predict the motion information of a static action image by exploiting unlabeled videos. We demonstrate the superiority of our framework based on four benchmark human action datasets with limited labeled data.

Published
2020-04-03
Section
AAAI Technical Track: Vision