GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer

08/28/2021
by   Shuaicheng Li, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 8

research
02/28/2023

Knowledge Augmented Relation Inference for Group Activity Recognition

Most existing group activity recognition methods construct spatial-tempo...
research
03/28/2020

Actor-Transformers for Group Activity Recognition

This paper strives to recognize individual actions and group activities ...
research
11/17/2022

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

The main streams of human activity recognition (HAR) algorithms are deve...
research
08/17/2023

Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction

Exploring spatial-temporal dependencies from observed motions is one of ...
research
01/05/2021

Bayesian hierarchical modeling and analysis for physical activity trajectories using actigraph data

Rapid developments in streaming data technologies are continuing to gene...
research
05/22/2019

Multi-agent Attentional Activity Recognition

Multi-modality is an important feature of sensor based activity recognit...
research
12/06/2018

Tri-axial Self-Attention for Concurrent Activity Recognition

We present a system for concurrent activity recognition. To extract feat...

Please sign up or login with your details

Forgot password? Click here to reset