{"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/why-cant-i-dance-in-the-mall-learning-to-1","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","arxiv_id":"1912.05534","date":"2019-12-11","proceeding":"NeurIPS 2019 12","authors":["Jinwoo Choi","Chen Gao","Joseph C. E. Messou","Jia-Bin Huang"],"abstract":"Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual discriminative cues). The learned representation may not generalize well to new action classes or different tasks. In this paper, we propose to mitigate scene bias for video representation learning. Specifically, we augment the standard cross-entropy loss for action classification with 1) an adversarial loss for scene types and 2) a human mask confusion loss for videos where the human actors are masked out. These two losses encourage learning representations that are unable to predict the scene types and the correct actions when there is no evidence. We validate the effectiveness of our method by transferring our pre-trained model to three different tasks, including action classification, temporal localization, and spatio-temporal action detection. Our results show consistent improvement over the baseline model without debiasing.","url_abs":"https://arxiv.org/abs/1912.05534v1","url_pdf":"https://arxiv.org/pdf/1912.05534v1.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":"why-cant-i-dance-in-the-mall-learning-to-1","repo_url":"https://github.com/vt-vl-lab/SDN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.05534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05534"}},"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/vt-vl-lab/SDN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"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":"vt-vl-lab/SDN","repo_kind":"official","path":"models/pre_act_resnet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/pre_act_resnet.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":"vt-vl-lab/SDN","repo_kind":"official","path":"models/pre_act_resnet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/pre_act_resnet.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":"vt-vl-lab/SDN","repo_kind":"official","path":"models/pre_act_resnet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/pre_act_resnet.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":"1df9a5ffd9b38c34","entry":"pil_loader","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"datasets/activitynet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/datasets/activitynet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1df9a5ffd9b38c34"}},{"code_sha256_prefix":"6921f7ed00595a4f","entry":"vgg","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"models/vgg.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/vgg.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":"6921f7ed00595a4f"}},{"code_sha256_prefix":"aae0a4f3535e8f26","entry":"accimage_loader","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"datasets/activitynet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/datasets/activitynet.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":"aae0a4f3535e8f26"}},{"code_sha256_prefix":"73ac7114d33b3e4f","entry":"accimage_loader","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"datasets/kinetics.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/datasets/kinetics.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":"73ac7114d33b3e4f"}},{"code_sha256_prefix":"95d9eef25c0060ed","entry":"get_adv_fine_tuning_parameters","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"models/vgg.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/vgg.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":"95d9eef25c0060ed"}},{"code_sha256_prefix":"b934dfd4a7bd8467","entry":"get_fine_tuning_parameters","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"models/densenet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/densenet.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":"b934dfd4a7bd8467"}},{"code_sha256_prefix":"b7aa932088b177a2","entry":"get_fine_tuning_parameters","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"models/vgg.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/models/vgg.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":"b7aa932088b177a2"}},{"code_sha256_prefix":"4b0838a32c3a88a2","entry":"pil_loader","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"datasets/kinetics.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/datasets/kinetics.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":"4b0838a32c3a88a2"}},{"code_sha256_prefix":"969914385b6159ef","entry":"video_loader","repo":"vt-vl-lab/SDN","repo_kind":"official","path":"datasets/activitynet.py","file_url":"https://github.com/vt-vl-lab/SDN/blob/HEAD/datasets/activitynet.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":"969914385b6159ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}