{"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/spatio-temporal-dynamic-inference-network-for","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","arxiv_id":"2108.11743","date":"2021-08-26","proceeding":"ICCV 2021 10","authors":["Hangjie Yuan","Dong Ni","Mang Wang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2108.11743v1","url_pdf":"https://arxiv.org/pdf/2108.11743v1.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":"spatio-temporal-dynamic-inference-network-for","repo_url":"https://github.com/jacobyuan7/din_gar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spatio-temporal-dynamic-inference-network-for","repo_url":"https://github.com/JacobYuan7/DIN-Group-Activity-Recognition-Benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"group-activity-recognition","task_name":"Group Activity Recognition"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/group-activity-recognition-on-volleyball","task":"Group Activity Recognition","dataset":"Volleyball","model":"DIN (VGG16)","rank_in_archive_order":3,"of":12,"metrics":{"Accuracy":"93.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.11743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11743"}},"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/jacobyuan7/din_gar","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JacobYuan7/DIN-Group-Activity-Recognition-Benchmark","reach":null}],"summary":{"ran":1,"unverified":11},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1},"listed":{"samples":2,"ran":1,"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":"0eed460a3795e49d","entry":"Dynamic_Person_Inference","repo":"JacobYuan7/DIN-Group-Activity-Recognition-Benchmark","repo_kind":"listed","path":"infer_module/dynamic_infer_module.py","file_url":"https://github.com/JacobYuan7/DIN-Group-Activity-Recognition-Benchmark/blob/HEAD/infer_module/dynamic_infer_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0eed460a3795e49d"}},{"code_sha256_prefix":"9042354c1505fdaa","entry":"collective_all_frames","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"collective.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/collective.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":"9042354c1505fdaa"}},{"code_sha256_prefix":"4ace51a89549296c","entry":"collective_read_annotations","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"collective.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/collective.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":"4ace51a89549296c"}},{"code_sha256_prefix":"f237616dbb3d98b9","entry":"collective_read_dataset","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"collective.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/collective.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":"f237616dbb3d98b9"}},{"code_sha256_prefix":"6f3f9960fe07ddf5","entry":"print_log","repo":"JacobYuan7/DIN-Group-Activity-Recognition-Benchmark","repo_kind":"listed","path":"infer_module/dynamic_infer_module.py","file_url":"https://github.com/JacobYuan7/DIN-Group-Activity-Recognition-Benchmark/blob/HEAD/infer_module/dynamic_infer_module.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":"6f3f9960fe07ddf5"}},{"code_sha256_prefix":"50380e8c37e9f408","entry":"return_dataset","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/dataset.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":"50380e8c37e9f408"}},{"code_sha256_prefix":"2abf049f07d06c77","entry":"test_volleyball","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net.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":"2abf049f07d06c77"}},{"code_sha256_prefix":"ef5bcfaacaa1e87e","entry":"test_volleyball","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net_dynamic.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net_dynamic.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":"ef5bcfaacaa1e87e"}},{"code_sha256_prefix":"17d5b498d50e7ddd","entry":"train_collective","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net.py","link_basis":"plan_row","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":"17d5b498d50e7ddd"}},{"code_sha256_prefix":"1f8d5e5eca3b206f","entry":"train_collective","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net_dynamic.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net_dynamic.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":"1f8d5e5eca3b206f"}},{"code_sha256_prefix":"59684e160d4e51f8","entry":"train_volleyball","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net.py","link_basis":"plan_row","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":"59684e160d4e51f8"}},{"code_sha256_prefix":"04b1defe9f81fa3a","entry":"train_volleyball","repo":"jacobyuan7/din_gar","repo_kind":"official","path":"train_net_dynamic.py","file_url":"https://github.com/jacobyuan7/din_gar/blob/HEAD/train_net_dynamic.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":"04b1defe9f81fa3a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}