ActionCLIP: A New Paradigm for Video Action Recognition

TL;DR

ActionCLIP introduces a multimodal video-text matching framework for action recognition, enabling zero-shot and few-shot learning with improved transferability and state-of-the-art accuracy on Kinetics-400.

Contribution

It proposes a new paradigm 'pre-train, prompt and fine-tune' for action recognition, leveraging large-scale web data and semantic label texts to enhance transferability.

Findings

Achieves 83.8% top-1 accuracy on Kinetics-400.

Demonstrates superior zero-shot and few-shot transfer capabilities.

Outperforms existing methods in general action recognition tasks.

Abstract

The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new datasets with unseen concepts. In this paper, we provide a new perspective on action recognition by attaching importance to the semantic information of label texts rather than simply mapping them into numbers. Specifically, we model this task as a video-text matching problem within a multimodal learning framework, which strengthens the video representation with more semantic language supervision and enables our model to do zero-shot action recognition without any further labeled data or parameters requirements. Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune". This paradigm first learns powerful representations from pre-training on a large amount of web image-text or video-text data. Then it makes the action recognition task to act more like pre-training problems via prompt engineering. Finally, it end-to-end fine-tunes on target datasets to obtain strong performance. We give an instantiation of the new paradigm, ActionCLIP, which not only has superior and flexible zero-shot/few-shot transfer ability but also reaches a top performance on general action recognition task, achieving 83.8% top-1 accuracy on Kinetics-400 with a ViT-B/16 as the backbone. Code is available at https://github.com/sallymmx/ActionCLIP.git