Papers › Home Action Genome: Cooperative Compositional Action Understanding

Home Action Genome: Cooperative Compositional Action Understanding

11 May 2021CVPR 2021 1arXiv:2105.05226archive 2025-07-28

Nishant Rai, Haofeng Chen, Jingwei Ji, Rishi Desai, Kazuki Kozuka, Shun Ishizaka, Ehsan Adeli, Juan Carlos Niebles

Existing research on action recognition treats activities as monolithic events occurring in videos. Recently, the benefits of formulating actions as a combination of atomic-actions have shown promise in improving action understanding with the emergence of datasets containing such annotations, allowing us to learn representations capturing this information. However, there remains a lack of studies that extend action composition and leverage multiple viewpoints and multiple modalities of data for representation learning. To promote research in this direction, we introduce Home Action Genome (HOMAGE): a multi-view action dataset with multiple modalities and view-points supplemented with hierarchical activity and atomic action labels together with dense scene composition labels. Leveraging rich multi-modal and multi-view settings, we propose Cooperative Compositional Action Understanding (CCAU), a cooperative learning framework for hierarchical action recognition that is aware of compositional action elements. CCAU shows consistent performance improvements across all modalities. Furthermore, we demonstrate the utility of co-learning compositions in few-shot action recognition by achieving 28.6% mAP with just a single sample.

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="2105.05226")

Code

Syntology Ran 2 of 16 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nishantrai18/homage officialmentioned 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

16 samples harvested; 2 ran; 0 honoured the contract we drafted; 14 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 · our draft was wrong
1ran
14unverified

Licence: 0 of the 16 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 nishantrai18/homage. “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.

downsample_basic_block nishantrai18/homage/backbone/resnet_2d3d.py official repository ran · our draft was wrong MIT (permissive) · 43c0211ff8dbca5f · report
make_layers nishantrai18/homage/backbone/vgg.py official repository ran MIT (permissive) · ac62432dc5134b0d · report
check_exists nishantrai18/homage/process_data/src/write_csv.py official repository unverified MIT (permissive) · e5e9f599c7fb5c8e · report
conv1x3x3 nishantrai18/homage/backbone/resnet_2d3d.py official repository unverified MIT (permissive) · 931634839b156bde · report
conv3x3x3 nishantrai18/homage/backbone/resnet_2d3d.py official repository unverified MIT (permissive) · 87ddd63faa8e7182 · report
get_modality_restore_ckpts nishantrai18/homage/train/model_trainer.py official repository unverified MIT (permissive) · ce8a65abcdc54d9f · report
get_num_classes nishantrai18/homage/train/model_utils.py official repository unverified MIT (permissive) · d44d97ff27bc2448 · report
get_parallel_model nishantrai18/homage/train/model_3d.py official repository unverified MIT (permissive) · abd535e179dd007b · report
get_split nishantrai18/homage/process_data/src/write_csv.py official repository unverified MIT (permissive) · 9075ce1ec911ec14 · report
individual_collate nishantrai18/homage/process_data/src/extract_features.py official repository unverified MIT (permissive) · a4228a80e45ad6c4 · report
num_frames_in_vid nishantrai18/homage/process_data/src/build_rawframes_optimized.py official repository unverified MIT (permissive) · 72884b5b5ef57fbe · report
resize_dim nishantrai18/homage/process_data/src/extract_frame.py official repository unverified MIT (permissive) · e164a1c87d234774 · report
run_optical_flow nishantrai18/homage/process_data/src/build_rawframes_optimized.py official repository unverified MIT (permissive) · 47d79b15733e0bb5 · report
select_resnet nishantrai18/homage/backbone/select_backbone.py official repository unverified MIT (permissive) · bd35fc73de072b28 · report
str2bool nishantrai18/homage/train/model_utils.py official repository unverified MIT (permissive) · 2ad736623a0c014d · report
str2list nishantrai18/homage/train/model_utils.py official repository unverified MIT (permissive) · 98d530cd4dcc1038 · report

Tasks

Action RecognitionAction UnderstandingFew Shot Action RecognitionFew-Shot action recognitionRepresentation LearningVideo Classification

Datasets

Introduced by this paper, per the archive.

Home Action Genome

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Classification Home Action Genome Cooperative Ours (3rd-person) Accuracy (%) 24.7 #1 of 1 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.

Methods

AWARE

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