{"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/ha-vid-a-human-assembly-video-dataset-for","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","arxiv_id":"2307.05721","date":"2023-07-09","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.","url_abs":"https://arxiv.org/abs/2307.05721v1","url_pdf":"https://arxiv.org/pdf/2307.05721v1.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":"ha-vid-a-human-assembly-video-dataset-for","repo_url":"https://github.com/iai-hrc/ha-vid","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.05721","atlas_url":"https://app.syntology.ai/?focus=2307.05721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05721"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/iai-hrc/ha-vid","reach":{"status":"ok"}}],"summary":{"ran":10,"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"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":12,"samples":[{"code_sha256_prefix":"3578ae2fe37218e3","entry":"BGM_loss_calc","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/BCN/bgm_block/loss_function.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/BCN/bgm_block/loss_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3578ae2fe37218e3"}},{"code_sha256_prefix":"a56fb39ace6cc0ac","entry":"BGM_loss_function","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/BCN/bgm_block/loss_function.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/BCN/bgm_block/loss_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a56fb39ace6cc0ac"}},{"code_sha256_prefix":"e7836f24ebf9eb94","entry":"bi_loss","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/BCN/bgm_block/loss_function.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/BCN/bgm_block/loss_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7836f24ebf9eb94"}},{"code_sha256_prefix":"4c49f489bd00e27e","entry":"dual_barrier_weight","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/BCN/lbp.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/BCN/lbp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c49f489bd00e27e"}},{"code_sha256_prefix":"2b315b1f11718511","entry":"exchange_time","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/DTGRM/layers.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/DTGRM/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b315b1f11718511"}},{"code_sha256_prefix":"c257ac36cba643a2","entry":"get_hop_distance","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/mmskeleton/graph.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/mmskeleton/graph.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c257ac36cba643a2"}},{"code_sha256_prefix":"8158f4435afa26b7","entry":"normalize_digraph","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/mmskeleton/graph.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/mmskeleton/graph.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8158f4435afa26b7"}},{"code_sha256_prefix":"f3dfe2628c96a73d","entry":"normalize_undigraph","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/mmskeleton/graph.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/mmskeleton/graph.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3dfe2628c96a73d"}},{"code_sha256_prefix":"a368cf4d78c78e3d","entry":"return_assembly","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/TSM/dataset_config.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/TSM/dataset_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a368cf4d78c78e3d"}},{"code_sha256_prefix":"7420ebb69beb5e09","entry":"return_dataset","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/TSM/dataset_config.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/TSM/dataset_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7420ebb69beb5e09"}},{"code_sha256_prefix":"591149e391b0f310","entry":"return_kinetics","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionRecognition/TSM/dataset_config.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionRecognition/TSM/dataset_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"591149e391b0f310"}},{"code_sha256_prefix":"2c3396349c49bcfb","entry":"unfold_1d","repo":"iai-hrc/ha-vid","repo_kind":"official","path":"ActionSegmentation/BCN/lbp.py","file_url":"https://github.com/iai-hrc/ha-vid/blob/HEAD/ActionSegmentation/BCN/lbp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c3396349c49bcfb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}