IMC 1 Lab
GraphSAGE-GRU Spatio-Temporal Sports Activity Recognition
Graph Neural Network + GRU for Collective Sports Modeling
Dr Adnan Zaryab
Project Overview
Combines Graph Neural Networks with Gated Recurrent Units for collective sports activity modeling. The GraphSAGE architecture samples and aggregates neighborhood features while GRU layers model sequential dependencies, enabling accurate recognition of team formations, player roles, and tactical movements in team sports.
System Architecture
Inputs
Multi-Cam Video
Processing Pipeline
Player Detection
GraphSAGE
GRU Temporal
Formation Decoder
Outputs
Team Formation
Role Classification
Related Publications (8)
Curated from publications by Dr. Adnan Ahmad Rafique
2025conference
Health Gaming based Activity Recognition Using Body-Worn Sensors via Artificial Neural Network
ComTech\'25, 2025
View on Scholar2026journal
MAGCS-AFF: A Graph-Cut and Attention Fusion Framework for Object Recognition in Complex Natural Scenes
KHI HTC 2026, 2026
View on Scholar2025conference
Revolutionizing Exergaming: Cutting-Edge Gesture Recognition for Immersive Fitness Experiences
ComTech\'25, 2025
View on Scholar2023conference
Semantic Segmentation and Feature Fusion based Scene Recognition via Deep Belief Network
ICACS23, 2023
View on Scholar2021journal
Scene Semantic recognition based on modified Fuzzy c-mean and maximum entropy using object-to-object relations
IEEE Access 9, 2021
View on Scholar2020journal
Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron
Symmetry, 2020
View on Scholar2019journal
Scene Understanding and Recognition: Statistical Segmented Model using Geometrical Features and Gaussian Na+�-�ve Bayes
Applied and Engineering Mathematics, 2019
View on Scholar2019journal
Salient Segmentation based Object Detection and Recognition using Hybrid Genetic Transform
ICAEM, 2019
View on Scholar