Alternative Semantic Representations for Zero-Shot Human Action Recognition
arXiv:1706.09317
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 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.
Technical Report, School of Computer Science, The University of Manchester, Accepted to ECML-PKDD 2017
References in corpus (5)
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
- Multi-Cue Zero-Shot Learning with Strong Supervision
- Multi-Label Zero-Shot Learning via Concept Embedding