Skeleton-Based Group Activity Recognition via Spatial-Temporal Panoramic Graph

Z Li, X Chang, Y Li, J Su - European Conference on Computer Vision, 2025 - Springer
Abstract Group Activity Recognition aims to understand collective activities from videos.
Existing solutions primarily rely on the RGB modality, which encounters challenges such as …

Multi-scale motion-based relational reasoning for group activity recognition

Y Zheng, Z Wang, K Gu, L Wu, Z Li, Y Xiang - Engineering Applications of …, 2025 - Elsevier
Existing group activity recognition methods generally use optical flow image to represent
motion within videos, which often struggle to capture the movements of individuals …

MPT-PAR: Mix-Parameters Transformer for Panoramic Activity Recognition

W Gan, Y Sun, F Liu, X Luo - arXiv preprint arXiv:2408.00420, 2024 - arxiv.org
The objective of the panoramic activity recognition task is to identify behaviors at various
granularities within crowded and complex environments, encompassing individual actions …

Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition

MA Nugroho, S Woo, S Lee, J Park, Y Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Weakly-Supervised Group Activity Recognition (WSGAR) aims to understand the activity
performed together by a group of individuals with the video-level label and without actor …

Knowledge Augmented Relation Inference for Group Activity Recognition

Z Wang, Z Li, X Lang, Y Zheng, M Tian… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Group activity recognition is a challenging task because it involves diverse individual actions
and complex relations. Most existing methods enhance individual representation by …

ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality

G Xu, J Yin, F Zhou, Y Dang - arXiv preprint arXiv:2407.19820, 2024 - arxiv.org
Previous methods usually only extract the image modality's information to recognize group
activity. However, mining image information is approaching saturation, making it difficult to …

[HTML][HTML] Empowering Efficient Spatio-Temporal Learning with a 3D CNN for Pose-Based Action Recognition

Z Ren, X Xiao, H Nie - Sensors (Basel, Switzerland), 2024 - pmc.ncbi.nlm.nih.gov
Action recognition based on 3D heatmap volumes has received increasing attention recently
because it is suitable for application to 3D CNNs to improve the recognition performance of …

Exploring global context and position-aware representation for group activity recognition

Z Du, Q Wang - Image and Vision Computing, 2024 - Elsevier
This paper explores the context and position information in the scene for group activity
understanding. Firstly, previous group activity recognition methods strive to reason on …

Conversation Activity Recognition Using Interaction Video Sequences in Pedestrian Groups

W Ganaha, T Ozaki, M Inoue, M Nishiyama - International Conference on …, 2024 - Springer
We introduce a method for recognizing conversation activity in a group of people walking
outdoors using a color video sequence acquired from a camera. Many methods have been …

Contrastive Learning-Based Dual Path Fusion Network for Group Activity Recognition

R Fu, Z Li, Y Xiang, L Lu, R Ding, L Wu - Chinese Conference on Image …, 2024 - Springer
Group activity recognition (GAR) remains challenging due to the diverse interactions among
individuals across different group activities. Therefore, fully exploring the complex …