{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/home-action-genome-cooperative-compositional","title":"Home Action Genome: Cooperative Compositional Action Understanding","arxiv_id":"2105.05226","date":"2021-05-11","proceeding":"CVPR 2021 1","authors":["Nishant Rai","Haofeng Chen","Jingwei Ji","Rishi Desai","Kazuki Kozuka","Shun Ishizaka","Ehsan Adeli","Juan Carlos Niebles"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2105.05226v1","url_pdf":"https://arxiv.org/pdf/2105.05226v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"home-action-genome-cooperative-compositional","repo_url":"https://github.com/nishantrai18/homage","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-understanding","task_name":"Action Understanding"},{"task_slug":"few-shot-action-recognition","task_name":"Few Shot Action Recognition"},{"task_slug":"few-shot-action-recognition","task_name":"Few-Shot action recognition"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[{"slug":"home-action-genome","name":"Home Action Genome","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-classification-on-home-action-genome","task":"Video Classification","dataset":"Home Action Genome","model":"Cooperative Ours (3rd-person)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"24.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05226"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nishantrai18/homage","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":14},"by_repo_kind":{"official":{"samples":16,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"43c0211ff8dbca5f","entry":"downsample_basic_block","repo":"nishantrai18/homage","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/backbone/resnet_2d3d.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43c0211ff8dbca5f"}},{"code_sha256_prefix":"ac62432dc5134b0d","entry":"make_layers","repo":"nishantrai18/homage","repo_kind":"official","path":"backbone/vgg.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/backbone/vgg.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac62432dc5134b0d"}},{"code_sha256_prefix":"e5e9f599c7fb5c8e","entry":"check_exists","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/write_csv.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/write_csv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5e9f599c7fb5c8e"}},{"code_sha256_prefix":"931634839b156bde","entry":"conv1x3x3","repo":"nishantrai18/homage","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/backbone/resnet_2d3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"931634839b156bde"}},{"code_sha256_prefix":"87ddd63faa8e7182","entry":"conv3x3x3","repo":"nishantrai18/homage","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/backbone/resnet_2d3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87ddd63faa8e7182"}},{"code_sha256_prefix":"ce8a65abcdc54d9f","entry":"get_modality_restore_ckpts","repo":"nishantrai18/homage","repo_kind":"official","path":"train/model_trainer.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/train/model_trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce8a65abcdc54d9f"}},{"code_sha256_prefix":"d44d97ff27bc2448","entry":"get_num_classes","repo":"nishantrai18/homage","repo_kind":"official","path":"train/model_utils.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/train/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d44d97ff27bc2448"}},{"code_sha256_prefix":"abd535e179dd007b","entry":"get_parallel_model","repo":"nishantrai18/homage","repo_kind":"official","path":"train/model_3d.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/train/model_3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abd535e179dd007b"}},{"code_sha256_prefix":"9075ce1ec911ec14","entry":"get_split","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/write_csv.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/write_csv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9075ce1ec911ec14"}},{"code_sha256_prefix":"a4228a80e45ad6c4","entry":"individual_collate","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/extract_features.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/extract_features.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4228a80e45ad6c4"}},{"code_sha256_prefix":"72884b5b5ef57fbe","entry":"num_frames_in_vid","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/build_rawframes_optimized.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/build_rawframes_optimized.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72884b5b5ef57fbe"}},{"code_sha256_prefix":"e164a1c87d234774","entry":"resize_dim","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/extract_frame.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/extract_frame.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e164a1c87d234774"}},{"code_sha256_prefix":"47d79b15733e0bb5","entry":"run_optical_flow","repo":"nishantrai18/homage","repo_kind":"official","path":"process_data/src/build_rawframes_optimized.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/process_data/src/build_rawframes_optimized.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47d79b15733e0bb5"}},{"code_sha256_prefix":"bd35fc73de072b28","entry":"select_resnet","repo":"nishantrai18/homage","repo_kind":"official","path":"backbone/select_backbone.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/backbone/select_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd35fc73de072b28"}},{"code_sha256_prefix":"2ad736623a0c014d","entry":"str2bool","repo":"nishantrai18/homage","repo_kind":"official","path":"train/model_utils.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/train/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ad736623a0c014d"}},{"code_sha256_prefix":"98d530cd4dcc1038","entry":"str2list","repo":"nishantrai18/homage","repo_kind":"official","path":"train/model_utils.py","file_url":"https://github.com/nishantrai18/homage/blob/HEAD/train/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98d530cd4dcc1038"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}