Alternative Semantic Representations for Zero-Shot Human Action Recognition

28 Jun 2017  ·  Qian Wang, Ke Chen ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Zero-Shot Action Recognition HMDB51 ASR Top-1 Accuracy 21.8 # 22
Zero-Shot Action Recognition UCF101 ASR Top-1 Accuracy 24.4 # 22

Methods


No methods listed for this paper. Add relevant methods here