Group Activity Recognition

11 papers with code • 2 benchmarks • 2 datasets

Group Activity Recognition is a subset of human activity recognition problem which focuses on the collective behavior of a group of people, resulted from the individual actions of the persons and their interactions. Collective activity recognition is a basic task for automatic human behavior analysis in many areas like surveillance or sports videos.

Source: A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition

Most implemented papers

Revisiting Skeleton-based Action Recognition

kennymckormick/pyskl CVPR 2022

In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.

Learning Actor Relation Graphs for Group Activity Recognition

wjchaoGit/Group-Activity-Recognition CVPR 2019

To this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors.

Spatio-Temporal Dynamic Inference Network for Group Activity Recognition

jacobyuan7/din_gar ICCV 2021

Within each interaction field, we apply DR to predict the relation matrix and DW to predict the dynamic walk offsets in a joint-processing manner, thus forming a person-specific interaction graph.

A Hierarchical Deep Temporal Model for Group Activity Recognition

mostafa-saad/deep-activity-rec CVPR 2016

In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity.

Hierarchical Deep Temporal Models for Group Activity Recognition

mostafa-saad/deep-activity-rec 9 Jul 2016

In order to model both person-level and group-level dynamics, we present a 2-stage deep temporal model for the group activity recognition problem.

SBGAR: Semantics Based Group Activity Recognition

xincoder/SBGAR ICCV 2017

Activity recognition has become an important function in many emerging computer vision applications e. g. automatic video surveillance system, human-computer interaction application, and video recommendation system, etc.

Hierarchical Relational Networks for Group Activity Recognition and Retrieval

mostafa-saad/hierarchical-relational-network ECCV 2018

Second, we propose a Relational Autoencoder model for unsupervised learning of features for action and scene retrieval.

Improved Actor Relation Graph based Group Activity Recognition

kuangzijian/Improved-Actor-Relation-Graph-based-Group-Activity-Recognition 24 Oct 2020

We propose to use Normalized cross-correlation (NCC) and the sum of absolute differences (SAD) to calculate the pair-wise appearance similarity and build the actor relationship graph to allow the graph convolution network to learn how to classify group activities.

Learning Group Activities from Skeletons without Individual Action Labels

fabiozappo/SkeletonGroupActivityRecognition 14 May 2021

To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions.

Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping

chihina/Joint-Group-Activity-Recognition MVA 2021

This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition.