Cross-modal Representation Learning for Zero-shot Action Recognition

We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR). Our model employs a conceptually new pipeline by which visual representations are learned in conjunction with visual-semantic associations in an end-to-end manner. The model design provides a natural mechanism for visual and semantic representations to be learned in a shared knowledge space, whereby it encourages the learned visual embedding to be discriminative and more semantically consistent. In zero-shot inference, we devise a simple semantic transfer scheme that embeds semantic relatedness information between seen and unseen classes to composite unseen visual prototypes. Accordingly, the discriminative features in the visual structure could be preserved and exploited to alleviate the typical zero-shot issues of information loss, semantic gap, and the hubness problem. Under a rigorous zero-shot setting of not pre-training on additional datasets, the experiment results show our model considerably improves upon the state of the arts in ZSAR, reaching encouraging top-1 accuracy on UCF101, HMDB51, and ActivityNet benchmark datasets. Code will be made available.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Zero-Shot Action Recognition ActivityNet ResT Top-1 Accuracy 32.5 # 3
Zero-Shot Action Recognition HMDB51 ResT Top-1 Accuracy 41.1 # 8
Zero-Shot Action Recognition UCF101 ResT Top-1 Accuracy 58.7 # 7


No methods listed for this paper. Add relevant methods here