{"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/something-else-compositional-action","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","arxiv_id":"1912.09930","date":"2019-12-20","proceeding":"CVPR 2020 6","authors":["Joanna Materzynska","Tete Xiao","Roei Herzig","Huijuan Xu","Xiaolong Wang","Trevor Darrell"],"abstract":"Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task, but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category.","url_abs":"https://arxiv.org/abs/1912.09930v3","url_pdf":"https://arxiv.org/pdf/1912.09930v3.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":"something-else-compositional-action","repo_url":"https://github.com/joaanna/something_else","is_official":0,"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":"object","task_name":"Object"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09930"}},"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/joaanna/something_else","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"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":"c3b215555357b9d1","entry":"conv3x3x3","repo":"joaanna/something_else","repo_kind":"listed","path":"code/model/resnet3d_xl.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/model/resnet3d_xl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3b215555357b9d1"}},{"code_sha256_prefix":"43c0211ff8dbca5f","entry":"downsample_basic_block","repo":"joaanna/something_else","repo_kind":"listed","path":"code/model/resnet3d_xl.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/model/resnet3d_xl.py","link_basis":"harvester_set","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":"93801ecf3026ab06","entry":"get_fine_tuning_parameters","repo":"joaanna/something_else","repo_kind":"listed","path":"code/model/resnet3d_xl.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/model/resnet3d_xl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93801ecf3026ab06"}},{"code_sha256_prefix":"3b4231faaa2a1a1f","entry":"config_init","repo":"joaanna/something_else","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/utils.py","link_basis":"harvester_set","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":"3b4231faaa2a1a1f"}},{"code_sha256_prefix":"782aac5ae40da2d7","entry":"get_colormap","repo":"joaanna/something_else","repo_kind":"listed","path":"annotate_videos.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/annotate_videos.py","link_basis":"harvester_set","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":"782aac5ae40da2d7"}},{"code_sha256_prefix":"37199776c5307977","entry":"load_json_config","repo":"joaanna/something_else","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/utils.py","link_basis":"harvester_set","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":"37199776c5307977"}},{"code_sha256_prefix":"d22081e20c57dcc9","entry":"remove_module_from_checkpoint_state_dict","repo":"joaanna/something_else","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/joaanna/something_else/blob/HEAD/code/utils.py","link_basis":"harvester_set","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":"d22081e20c57dcc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}