GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer

TL;DR

GroupFormer is a novel transformer-based model that jointly captures spatial-temporal interactions for group activity recognition, outperforming previous methods on key datasets.

Contribution

It introduces a clustered spatial-temporal transformer that models dependencies integrally and dynamically clusters individuals for improved semantic representations.

Findings

Outperforms state-of-the-art on Volleyball dataset

Outperforms state-of-the-art on Collective Activity dataset

Effectively models spatial-temporal dependencies

Abstract

Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model spatial and temporal information separately, or directly aggregate individual features to form group features. To address these issues, we propose a novel group activity recognition network termed GroupFormer. It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer. Specifically, our GroupFormer has three appealing advantages: (1) A tailor-modified Transformer, Clustered Spatial-Temporal Transformer, is proposed to enhance the individual representation and group representation. (2) It models the spatial and temporal dependencies integrally and utilizes decoders to build the bridge between the spatial and temporal information. (3) A clustered attention mechanism is utilized to dynamically divide individuals into multiple clusters for better learning activity-aware semantic representations. Moreover, experimental results show that the proposed framework outperforms state-of-the-art methods on the Volleyball dataset and Collective Activity dataset. Code is available at https://github.com/xueyee/GroupFormer.