Papers › Spatio-Temporal Dynamic Inference Network for Group Activity Recognition

Spatio-Temporal Dynamic Inference Network for Group Activity Recognition

26 Aug 2021ICCV 2021 10arXiv:2108.11743archive 2025-07-28

Hangjie Yuan, Dong Ni, Mang Wang

Group activity recognition aims to understand the activity performed by a group of people. In order to solve it, modeling complex spatio-temporal interactions is the key. Previous methods are limited in reasoning on a predefined graph, which ignores the inherent person-specific interaction context. Moreover, they adopt inference schemes that are computationally expensive and easily result in the over-smoothing problem. In this paper, we manage to achieve spatio-temporal person-specific inferences by proposing Dynamic Inference Network (DIN), which composes of Dynamic Relation (DR) module and Dynamic Walk (DW) module. We firstly propose to initialize interaction fields on a primary spatio-temporal graph. 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. By updating features on the specific graph, a person can possess a global-level interaction field with a local initialization. Experiments indicate both modules' effectiveness. Moreover, DIN achieves significant improvement compared to previous state-of-the-art methods on two popular datasets under the same setting, while costing much less computation overhead of the reasoning module.

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="2108.11743")

Code

Syntology Ran 1 of 12 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 0 ran; community (archive-listed): 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jacobyuan7/din_gar officialmentioned in papermentioned on GitHubpytorchMIT 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

12 samples harvested; 1 ran; 0 honoured the contract we drafted; 11 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.

1ran
11unverified

Licence: 0 of the 12 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

collective_all_frames jacobyuan7/din_gar/collective.py official repository unverified MIT (permissive) · 9042354c1505fdaa · report
collective_read_annotations jacobyuan7/din_gar/collective.py official repository unverified MIT (permissive) · 4ace51a89549296c · report
collective_read_dataset jacobyuan7/din_gar/collective.py official repository unverified MIT (permissive) · f237616dbb3d98b9 · report
return_dataset jacobyuan7/din_gar/dataset.py official repository unverified MIT (permissive) · 50380e8c37e9f408 · report
test_volleyball jacobyuan7/din_gar/train_net.py official repository unverified MIT (permissive) · 2abf049f07d06c77 · report
test_volleyball jacobyuan7/din_gar/train_net_dynamic.py official repository unverified MIT (permissive) · ef5bcfaacaa1e87e · report
train_collective jacobyuan7/din_gar/train_net.py official repository unverified MIT (permissive) · 17d5b498d50e7ddd · report
train_collective jacobyuan7/din_gar/train_net_dynamic.py official repository unverified MIT (permissive) · 1f8d5e5eca3b206f · report
train_volleyball jacobyuan7/din_gar/train_net.py official repository unverified MIT (permissive) · 59684e160d4e51f8 · report
train_volleyball jacobyuan7/din_gar/train_net_dynamic.py official repository unverified MIT (permissive) · 04b1defe9f81fa3a · report
Dynamic_Person_Inference JacobYuan7/DIN-Group-Activity-Recognition-Benchmark/infer_module/dynamic_infer_module.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 0eed460a3795e49d · report
print_log JacobYuan7/DIN-Group-Activity-Recognition-Benchmark/infer_module/dynamic_infer_module.py community (archive-listed) unverified MIT (permissive) · 6f3f9960fe07ddf5 · report

Tasks

Activity RecognitionGroup Activity Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Group Activity Recognition Volleyball DIN (VGG16) Accuracy 93.6 #3 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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