Alternative Semantic Representations for Zero-Shot Human Action Recognition
This work addresses the problem of scalable zero-shot learning for human action recognition by leveraging low-cost web data, offering an incremental improvement over existing methods.
The paper tackles zero-shot human action recognition by exploring text descriptions and deep image features as alternative semantic representations, which outperform traditional attributes and word vectors on UCF101 and HMDB51 datasets, with image-based representations achieving favorable performance even with few images per class.
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.