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 way in 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 number of images per class.



Side Information Collection

Experimental Results

Codes and Data

If you are interested in our work, the codes and data (e.g., pre-computed visual representations, semantic representations used in our experiments) are available upon request. The details of the codes and data are described here.

[download data] [download imageScraperTool]

Qian Wang


Related Paper

Wang, Q. and Chen, K. (2017). Alternative Semantic Representations for Zero-Shot Human Action Recognition. Proc.ECML-PKDD 2017.