Papers › GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer

GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer

28 Aug 2021ICCV 2021 10arXiv:2108.12630archive 2025-07-28

Shuaicheng Li, Qianggang Cao, Lingbo Liu, Kunlin Yang, Shinan Liu, Jun Hou, Shuai Yi

Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model spatial and temporal information separately, or directly aggregate individual features to form group features. To address these issues, we propose a novel group activity recognition network termed GroupFormer. It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer. Specifically, our GroupFormer has three appealing advantages: (1) A tailor-modified Transformer, Clustered Spatial-Temporal Transformer, is proposed to enhance the individual representation and group representation. (2) It models the spatial and temporal dependencies integrally and utilizes decoders to build the bridge between the spatial and temporal information. (3) A clustered attention mechanism is utilized to dynamically divide individuals into multiple clusters for better learning activity-aware semantic representations. Moreover, experimental results show that the proposed framework outperforms state-of-the-art methods on the Volleyball dataset and Collective Activity dataset. Code is available at https://github.com/xueyee/GroupFormer.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.12630")

Code

Syntology Ran 19 of 27 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 3 ran · honoured contract; 13 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 25 samples from 1 repository, 17 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xueyee/groupformer officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

27 samples harvested; 19 ran; 3 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
13ran · our draft was wrong
1ran · fixture could not drive it
2ran
8unverified

Licence: 2 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xueyee/GroupFormer. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Kmeans xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · c125449e7df4ac6d · report
KmeansAttention xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · daba1d12c937fb50 · report
batched_bincount xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 3c9e316e182b4d7d · report
batched_index_select xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 098a5dd15c0b4167 · report
cast_tuple xueyee/groupformer/group/models/cluster_transformer.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0b73c0c3c680d31 · report
default xueyee/groupformer/group/models/cluster_transformer.py official repository ran · honoured contract Apache-2.0 (permissive) · ebbe83e33bdee406 · report
distribution xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c88722608edfbb70 · report
dists_and_buckets xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 45afc9429eea1b63 · report
ema xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · f70774c0916069a5 · report
kmeans_iter xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 266f3de8e8cd3655 · report
max_neg_value xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b209878199e80c50 · report
reshape_dim xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 2866aa5c23d64139 · report
scatter_mean xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · e437fa79b7c02bfb · report
similarity xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 4d588005f814f46d · report
split_at_index xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 79eb67938353bd45 · report
to xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · f092dd8a37a00a6e · report
update_kmeans_on_backwards xueyee/GroupFormer/group/models/cluster_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 1643840480c9ad87 · report
ClusteringTransformer xueyee/GroupFormer/group/models/cluster_transformer.py official repository unverified Apache-2.0 (permissive) · 208f65adecf9a0f7 · report
SelfAttention xueyee/GroupFormer/group/models/cluster_transformer.py official repository unverified Apache-2.0 (permissive) · 76f9cb9ada2064dc · report
build_transformer xueyee/groupformer/group/models/transformer.py official repository unverified Apache-2.0 (permissive) · 302ec916d91b12a8 · report
cache_fn xueyee/groupformer/group/models/cluster_transformer.py official repository unverified Apache-2.0 (permissive) · c849eae4bd18f599 · report
multi_head_attention_forward xueyee/groupformer/group/models/transformer_cluster.py official repository unverified Apache-2.0 (permissive) · 8e2156fc442de944 · report
volley_all_frames xueyee/groupformer/group/datasets/volleyball.py official repository unverified Apache-2.0 (permissive) · 415a573251464da5 · report
volley_read_annotations xueyee/groupformer/group/datasets/volleyball.py official repository unverified Apache-2.0 (permissive) · ca074ca0c718a909 · report
volley_read_dataset xueyee/groupformer/group/datasets/volleyball.py official repository unverified Apache-2.0 (permissive) · 1bf81af39059aefe · report
expand_dim identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 270b669b4662f5c1 · report
find_modules identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 4e291c3ece372165 · report

Tasks

Activity RecognitionGroup Activity Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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