Exploring Semantic Inter-Class Relationships (SIR) for Zero-Shot Action Recognition

Publisher:
AAAI
Publication Type:
Conference Proceeding
Citation:
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015, pp. 3769 - 3775
Issue Date:
2015-01-01
Full metadata record
Files in This Item:
Filename Description Size
9929-44990-1-PB.pdfPublished version6.47 MB
Adobe PDF
Automatically recognizing a large number of action categories from videos is of significant importance for video understanding. Most existing works focused on the design of more discriminative feature representation, and have achieved promising results when the positive samples are enough. However, very limited efforts were spent on recognizing a novel action without any positive exemplars, which is often the case in the real settings due to the large amount of action classes and the users' queries dramatic variations. To address this issue, we propose to perform action recognition when no positive exemplars of that class are provided, which is often known as the zero-shot learning. Different from other zero-shot learning approaches, which exploit attributes as the intermediate layer for the knowledge transfer, our main contribution is SIR, which directly leverages the semantic inter-class relationships between the known and unknown actions followed by label transfer learning. The inter-class semantic relationships are automatically measured by continuous word vectors, which learned by the skip-gram model using the large-scale text corpus. Extensive experiments on the UCF101 dataset validate the superiority of our method over fully-supervised approaches using few positive exemplars
Please use this identifier to cite or link to this item: