Progressive Relation Learning for Group Activity Recognition

08/08/2019
by   Guyue Hu, et al.
2

Group activities usually involve spatio-temporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Therefore, effectively modeling the group-relevant and suppressing the irrelevant actions (and interactions) are vital for group activity recognition. In this paper, we propose a novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities. Firstly, we construct a semantic relation graph (SRG) to explicitly model the relations among persons. Then, two agents adopting policy according to two Markov decision processes are applied to progressively refine the SRG. Specifically, one feature-distilling (FD) agent in the discrete action space refines the low-level spatio-temporal features by distilling the most informative frames. Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations. The SRG, FD agent, and RG agent are optimized alternately to mutually boost the performance of each other. Extensive experiments on two widely used benchmarks demonstrate the effectiveness and superiority of the proposed approach.

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
08/27/2019

Temporal Reasoning Graph for Activity Recognition

Despite great success has been achieved in activity analysis, it still h...
research
08/26/2021

Spatio-Temporal Dynamic Inference Network for Group Activity Recognition

Group activity recognition aims to understand the activity performed by ...
research
08/06/2020

Group Activity Prediction with Sequential Relational Anticipation Model

In this paper, we propose a novel approach to predict group activities g...
research
02/06/2015

Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel

Many visual recognition problems can be approached by counting instances...
research
04/18/2023

MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition

The task of Group Activity Recognition (GAR) aims to predict the activit...
research
08/21/2012

A Unified Approach for Modeling and Recognition of Individual Actions and Group Activities

Recognizing group activities is challenging due to the difficulties in i...

Please sign up or login with your details

Forgot password? Click here to reset