CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition

Zero-shot action recognition is the task of recognizing action classes without visual examples, only with a semantic embedding which relates unseen to seen classes. The problem can be seen as learning a function which generalizes well to instances of unseen classes without losing discrimination between classes. Neural networks can model the complex boundaries between visual classes, which explains their success as supervised models. However, in zero-shot learning, these highly specialized class boundaries may not transfer well from seen to unseen classes. In this paper, we propose a clustering-based model, which considers all training samples at once, instead of optimizing for each instance individually. We optimize the clustering using Reinforcement Learning which we show is critical for our approach to work. We call the proposed method CLASTER and observe that it consistently improves over the state-of-the-art in all standard datasets, UCF101, HMDB51, and Olympic Sports; both in the standard zero-shot evaluation and the generalized zero-shot learning.