Papers › GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2108.12630")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2108.12630", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2108.12630")
Code
Syntology 27 code samples: 25 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 27: 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. Where Syntology's instrument failed: 13 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 25 samples from 1 repository, 20 ran (8 with no instrument failure; 12 where Syntology's instrument failed); 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.
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
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. 2 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
c125449e7df4ac6d · report
fixture: returned Kmeans · level recorded 2026-09-22 daba1d12c937fb50 · report
fixture: returned KmeansAttention · level recorded 2026-09-22 3c9e316e182b4d7d · report
fixture: signature index:Tensor/2/int, num_classes:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-22 098a5dd15c0b4167 · report
fixture: signature values:Tensor/3/float, indices:Tensor/2/int · returned Tensor · level recorded 2026-09-22 c849eae4bd18f599 · report
fixture: signature f:callable/0/? · returned function · level recorded 2026-09-25 e0b73c0c3c680d31 · report
fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22 ebbe83e33bdee406 · report
fixture: signature x:NoneType/0/?, d:int/0/int · returned int · level recorded 2026-09-22 c88722608edfbb70 · report
fixture: signature dists:Tensor/3/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22 45afc9429eea1b63 · report
fixture: signature x:Tensor/4/float, means:Tensor/3/float · returned tuple · level recorded 2026-09-22 census: 4 implementations from 7 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 group/models/cluster_transformer.py ran · honoured contract fingerprinted Apache-2.0 (permissive) ·
f70774c0916069a5 · report
fixture: signature old:Tensor/2/float, new:Tensor/2/float, decay:float/0/float · returned Tensor · level recorded 2026-09-22 266f3de8e8cd3655 · report
fixture: signature x:Tensor/4/float, means:Tensor/3/float, buckets:Tensor/3/int · returned Tensor · level recorded 2026-09-22 census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 group/models/cluster_transformer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) ·
b209878199e80c50 · report
fixture: signature tensor:Tensor/2/float · returned float · level recorded 2026-09-22 8e2156fc442de944 · report
fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, embed_dim_to_check:int/0/int, num_heads:int/0/int, in_proj_weight:Tensor/2/float, in_proj_bias:Tensor/1/float, bias_k:NoneType/0/?, bias_v:NoneType/0/?, add_zero_attn:bool/0/bool, dropout_p:float/0/float, out_proj_weight:Tensor/2/float, out_proj_bias:Tensor/1/float, training:bool/0/bool, key_padding_mask:NoneType/0/?, need_weights:bool/0/bool, attn_mask:NoneType/0/?, use_separate_proj_weight:bool/0/bool, q_proj_weight:NoneType/0/?, k_proj_weight:NoneType/0/?, v_proj_weight:NoneType/0/?, static_k:NoneType/0/?, static_v:NoneType/0/? · returned tuple · level recorded 2026-09-25 2866aa5c23d64139 · report
fixture: signature t:Tensor/3/float, dim:int/0/int, split_dims:tuple/1/int · returned Tensor · level recorded 2026-09-22 e437fa79b7c02bfb · report
fixture: signature src:Tensor/2/float, t:Tensor/2/float, index:Tensor/2/int, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22 4d588005f814f46d · report
fixture: signature x:Tensor/4/float, means:Tensor/3/float · returned Tensor · level recorded 2026-09-22 79eb67938353bd45 · report
fixture: signature dim:int/0/int, index:int/0/int, t:Tensor/4/float · returned tuple · level recorded 2026-09-22 f092dd8a37a00a6e · report
fixture: signature t:Tensor/2/float · returned dict · level recorded 2026-09-22 1643840480c9ad87 · report
fixture: signature module:callable/0/? · returned RemovableHandle · level recorded 2026-09-22 415a573251464da5 · report
fixture: signature data:dict/0/? · returned list · level recorded 2026-09-25 208f65adecf9a0f7 · report
76f9cb9ada2064dc · report
302ec916d91b12a8 · report
ca074ca0c718a909 · report
1bf81af39059aefe · report
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded ·
270b669b4662f5c1 · report
fixture: signature t:Tensor/2/float, dim:int/0/int, k:int/0/int · returned Tensor · level recorded 2026-09-22 4e291c3ece372165 · report
fixture: signature nn_module:callable/0/?, type:callable/0/? · returned list · level recorded 2026-09-22 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for GroupFormer (graph method: GroupFormer). 20 bricks; individually on a fixture: 18 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 14 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
- ClusteringTransformer entry · level 0 · unverified ·
208f65adecf9a0f7 - SelfAttention model · level 0 · unverified ·
76f9cb9ada2064dc - default helper · level 1 · ran · honoured contract ·
ebbe83e33bdee406 - update_kmeans_on_backwards helper · level 1 · ran · our draft was wrong ·
1643840480c9ad87 - KmeansAttention model · level 1 · ran ·
daba1d12c937fb50 - reshape_dim helper · level 1 · ran · our draft was wrong ·
2866aa5c23d64139 - to helper · level 1 · ran · our draft was wrong ·
f092dd8a37a00a6e - Kmeans model · level 1 · ran ·
c125449e7df4ac6d - find_modules helper · level 1 · ran · our draft was wrong ·
4e291c3ece372165 - batched_index_select helper · level 1 · ran · our draft was wrong ·
098a5dd15c0b4167 - distribution helper · level 1 · ran · our draft was wrong ·
c88722608edfbb70 - expand_dim helper · level 1 · ran · our draft was wrong ·
270b669b4662f5c1 - max_neg_value helper · level 1 · ran · our draft was wrong ·
b209878199e80c50 - scatter_mean helper · level 1 · ran · our draft was wrong ·
e437fa79b7c02bfb - split_at_index helper · level 1 · ran · our draft was wrong ·
79eb67938353bd45 - dists_and_buckets helper · level 1 · ran · our draft was wrong ·
45afc9429eea1b63 - ema helper · level 1 · ran · honoured contract ·
f70774c0916069a5 - kmeans_iter helper · level 1 · ran; the contract check could not run (RAISES) ·
266f3de8e8cd3655 - similarity helper · level 1 · ran · our draft was wrong ·
4d588005f814f46d - batched_bincount helper · level 1 · ran · our draft was wrong ·
3c9e316e182b4d7d
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2108.12630") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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