Alternative Semantic Representations for Zero-Shot Human Action Recognition

Qian Wang, Ke Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

111 Downloads (Pure)

Abstract

A proper semantic representation for encoding side information is key to the success of zero-shot learning. In this paper, we explore two alternative semantic representations especially for zero-shot human action recognition: textual descriptions of human actions and deep features extracted from still images relevant to human actions. Such side information are accessible on Web with little cost, which paves a new wayin gaining side information for large-scale zero-shot human action recognition. We investigate different encoding methods to generate semantic representations for human actions from such side information. Based on our zero-shot visual recognition method, we conducted experiments on UCF101 and HMDB51 to evaluate two proposed semantic representations . The results suggest that our proposed text- and image-based semantic representations outperform traditional attributes and word vectors considerably for zero-shot human action recognition. In particular, the image-based semantic representations yield the favourable performance even though the representation is extracted from a small numberof images per class.
Original languageEnglish
Title of host publicationEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD 2017
DOIs
Publication statusPublished - 2017

Keywords

  • Zero-shot learning
  • Semantic representation
  • Human Ac- tion Recognition
  • Image Deep Representation
  • Textual Description Representation
  • Fisher Vector

Fingerprint

Dive into the research topics of 'Alternative Semantic Representations for Zero-Shot Human Action Recognition'. Together they form a unique fingerprint.

Cite this