Browse State-of-the-Art › Group Activity Recognition
Group Activity Recognition
18 papers with code · 2 benchmarks · 2 datasets archive 2025-07-28
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
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Volleyball (12 rows) | Tamura et al. | Hunting Group Clues with Transformers for Social Group Activity Recognition | — | — | Compare |
| Collective Activity (6 rows) | Tamura et al. | Hunting Group Clues with Transformers for Social Group Activity Recognition | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 65 · with a code link: 18 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 65 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 65 of 65, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
28 Apr 2021 4 repositories listedIn 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.
-
26 Aug 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified (of 12 harvested samples)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.
-
23 Apr 2019 2 repositories listedTo this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors.
-
9 Mar 2025 1 repository listedThis framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks.
-
9 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)To this end, we introduce a Convex Hull Adaptive Shift based multi-Entity action recognition method (CHASE), which mitigates inter-entity distribution gaps and unbiases subsequent backbones.
-
4 Sep 2024 1 repository listedOur key contribution is the introduction of a novel compositional query machine, called COMPUTER (COMPositional hUman-cenTric quERy machine), a generic neural architecture that models the interactions between a human of…
-
28 Jul 2024 1 repository listedTo address these limitations, we design a panoramic graph that incorporates multi-person skeletons and objects to encapsulate group activity, offering an effective alternative to RGB video.
-
11 Mar 2023 1 repository listedTo that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches.
-
6 Mar 2023 1 repository listedIn 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.
-
11 Dec 2021 1 repository listedGroup Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects.
-
28 Aug 2021 1 repository listed Syntology official (archive's flag): 20 ran · 22 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified (of 27 harvested samples) · 2 pointer-only (licence)It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer.
-
Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping17 Jul 2021 1 repository listedThis paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition.
-
14 May 2021 1 repository listedTo understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions.
-
24 Oct 2020 1 repository listedWe 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…
-
1 Sep 2018 1 repository listedSecond, we propose a Relational Autoencoder model for unsupervised learning of features for action and scene retrieval.
-
1 Oct 2017 1 repository listedActivity 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.
-
9 Jul 2016 1 repository listedIn order to model both person-level and group-level dynamics, we present a 2-stage deep temporal model for the group activity recognition problem.
-
19 Nov 2015 1 repository listedIn group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity.
-
PromptGAR: Flexible Promptive Group Activity Recognition11 Mar 2025 0 repositories listedWe present PromptGAR, a novel framework that addresses the limitations of current Group Activity Recognition (GAR) approaches by leveraging multi-modal prompts to achieve both input flexibility and high recognition…
-
ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition4 Nov 2024 0 repositories listedThis paper presents the ARN-LSTM architecture, a novel multi-stream action recognition model designed to address the challenge of simultaneously capturing spatial motion and temporal dynamics in action sequences.
-
LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition28 Oct 2024 0 repositories listedGroup Activity Recognition (GAR) remains challenging in computer vision due to the complex nature of multi-agent interactions.
-
Explainable Artificial Intelligence for Quantifying Interfering and High-Risk Behaviors in Autism Spectrum Disorder in a Real-World Classroom Environment Using Privacy-Preserving Video Analysis31 Jul 2024 0 repositories listedRapid identification and accurate documentation of interfering and high-risk behaviors in ASD, such as aggression, self-injury, disruption, and restricted repetitive behaviors, are important in daily classroom…
-
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality29 Jul 2024 0 repositories listedPrevious methods usually only extract the image modality's information to recognize group activity.
-
Self-supervised Multi-actor Social Activity Understanding in Streaming Videos20 Jun 2024 0 repositories listedThis work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics.
-
Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition28 May 2024 0 repositories listedWeakly-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-level labels.
-
Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition15 Apr 2024 0 repositories listedSocial group activity recognition is a challenging task extended from group activity recognition, where social groups must be recognized with their activities and group members.
-
Group Activity Recognition using Unreliable Tracked Pose6 Jan 2024 0 repositories listedGroup activity recognition in video is a complex task due to the need for a model to recognise the actions of all individuals in the video and their complex interactions.
-
Bi-Causal: Group Activity Recognition via Bidirectional Causality1 Jan 2024 0 repositories listedCurrent approaches in Group Activity Recognition (GAR) predominantly emphasize Human Relations (HRs) while often neglecting the impact of Human-Object Interactions (HOIs).
-
A Causality-Aware Pattern Mining Scheme for Group Activity Recognition in a Pervasive Sensor Space1 Dec 2023 0 repositories listedHuman activity recognition (HAR) is a key challenge in pervasive computing and its solutions have been presented based on various disciplines.
-
REACT: Recognize Every Action Everywhere All At Once27 Nov 2023 0 repositories listedGroup Activity Recognition (GAR) is a fundamental problem in computer vision, with diverse applications in sports video analysis, video surveillance, and social scene understanding.
-
Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives25 Jul 2023 0 repositories listed
-
M3Act: Learning from Synthetic Human Group Activities29 Jun 2023 0 repositories listed
-
Group Activity Recognition via Dynamic Composition and Interaction9 May 2023 0 repositories listed
-
SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition27 Apr 2023 0 repositories listed
-
MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition18 Apr 2023 0 repositories listed
-
Knowledge Augmented Relation Inference for Group Activity Recognition28 Feb 2023 0 repositories listed
-
An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity1 Jan 2023 0 repositories listed
-
Attentive pooling for Group Activity Recognition31 Aug 2022 0 repositories listed
-
Group Activity Recognition in Basketball Tracking Data -- Neural Embeddings in Team Sports (NETS)31 Aug 2022 0 repositories listed
-
12 Jul 2022 0 repositories listed
-
Detector-Free Weakly Supervised Group Activity Recognition5 Apr 2022 0 repositories listed
-
Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition5 Apr 2022 0 repositories listed
-
9 Aug 2021 0 repositories listed
-
Indoor Group Activity Recognition using Multi-Layered HMMs23 Jan 2021 0 repositories listed
-
Context Aware Group Activity Recognition1 Jan 2021 0 repositories listed
-
Skeleton-based Relational Reasoning for Group Activity Analysis11 Nov 2020 0 repositories listed
-
Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition1 Aug 2020 0 repositories listed
-
18 Jul 2020 0 repositories listed
-
Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos13 Jul 2020 0 repositories listed
-
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos6 Jul 2020 0 repositories listed
-
Actor-Transformers for Group Activity Recognition28 Mar 2020 0 repositories listed
-
10 Mar 2020 0 repositories listed
-
Progressive Relation Learning for Group Activity Recognition8 Aug 2019 0 repositories listed
-
Convolutional Relational Machine for Group Activity Recognition5 Apr 2019 0 repositories listed
-
A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition26 Dec 2018 0 repositories listed
-
Multi-Level Sequence GAN for Group Activity Recognition18 Dec 2018 0 repositories listed
-
stagNet: An Attentive Semantic RNN for Group Activity Recognition1 Sep 2018 0 repositories listed
-
Recurrent Modeling of Interaction Context for Collective Activity Recognition1 Jul 2017 0 repositories listed
-
10 Apr 2017 0 repositories listed
-
Learning Ensembles of Potential Functions for Structured Prediction With Latent Variables1 Dec 2015 0 repositories listed
-
13 Nov 2015 0 repositories listed
-
Deep Structured Models For Group Activity Recognition12 Jun 2015 0 repositories listed
-
A Heat-Map-based Algorithm for Recognizing Group Activities in Videos21 Feb 2015 0 repositories listed
-
A new network-based algorithm for human activity recognition in video21 Feb 2015 0 repositories listed
-
Relevance Topic Model for Unstructured Social Group Activity Recognition1 Dec 2013 0 repositories listed
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections