CLIP-guided Prototype Modulating for Few-shot Action Recognition

TL;DR

This paper introduces CLIP-FSAR, a framework that leverages CLIP's multimodal knowledge to improve few-shot action recognition by refining visual prototypes with semantic priors and contrastive learning.

Contribution

It proposes a novel CLIP-guided prototype modulation method combining contrastive learning and prototype refinement for low-data action recognition tasks.

Findings

Significantly outperforms existing methods on five benchmarks.

Effectively utilizes CLIP's semantic priors for prototype refinement.

Achieves robust few-shot classification with limited data.

Abstract

Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task. In this work, we aim to transfer the powerful multimodal knowledge of CLIP to alleviate the inaccurate prototype estimation issue due to data scarcity, which is a critical problem in low-shot regimes. To this end, we present a CLIP-guided prototype modulating framework called CLIP-FSAR, which consists of two key components: a video-text contrastive objective and a prototype modulation. Specifically, the former bridges the task discrepancy between CLIP and the few-shot video task by contrasting videos and corresponding class text descriptions. The latter leverages the transferable textual concepts from CLIP to adaptively refine visual prototypes with a temporal Transformer. By this means, CLIP-FSAR can take full advantage of the rich semantic priors in CLIP to obtain reliable prototypes and achieve accurate few-shot classification. Extensive experiments on five commonly used benchmarks demonstrate the effectiveness of our proposed method, and CLIP-FSAR significantly outperforms existing state-of-the-art methods under various settings. The source code and models will be publicly available at https://github.com/alibaba-mmai-research/CLIP-FSAR.