Group Activity Recognition
14 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
Latest papers
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image
To that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches.
SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition
In this paper, we propose a new, simple, and effective Self-supervised Spatio-temporal Transformers (SPARTAN) approach to Group Activity Recognition (GAR) using unlabeled video data.
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects.
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer.
Spatio-Temporal Dynamic Inference Network for Group Activity Recognition
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.
Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping
This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition.
Learning Group Activities from Skeletons without Individual Action Labels
To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions.
Revisiting Skeleton-based Action Recognition
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.
Improved Actor Relation Graph based Group Activity Recognition
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 Actor Relation Graphs for Group Activity Recognition
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.