Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

TL;DR

This paper introduces DiST, a novel framework leveraging large language models to decouple and incorporate spatial and temporal knowledge, significantly improving few-shot action recognition by learning detailed prototypes.

Contribution

The paper proposes a decoupled spatio-temporal knowledge framework using language models to enhance prototype learning in FSAR, which is a novel approach.

Findings

Achieves state-of-the-art results on five FSAR datasets.

Effectively captures fine-grained spatial details.

Models diverse temporal patterns.

Abstract

Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features. However, such context provided by the action names is too limited to provide sufficient background knowledge for capturing novel spatial and temporal concepts in actions. In this paper, we propose DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes. In the decomposition stage, we decouple vanilla action names into diverse spatio-temporal attribute descriptions (action-related knowledge). Such commonsense knowledge complements semantic contexts from spatial and temporal perspectives. In the incorporation stage, we propose Spatial/Temporal Knowledge Compensators (SKC/TKC) to discover discriminative object-level and frame-level prototypes, respectively. In SKC, object-level prototypes adaptively aggregate important patch tokens under the guidance of spatial knowledge. Moreover, in TKC, frame-level prototypes utilize temporal attributes to assist in inter-frame temporal relation modeling. These learned prototypes thus provide transparency in capturing fine-grained spatial details and diverse temporal patterns. Experimental results show DiST achieves state-of-the-art results on five standard FSAR datasets.