{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/toyota-smarthome","name":"Toyota Smarthome Dataset","full_name":null,"description_markdown":"A large scale dataset with daily-living activities performed in a natural manner.\r\n\r\nSource: [Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection](/paper/toyota-smarthome-untrimmed-real-world)","description_withheld":null,"homepage":"https://project.inria.fr/toyotasmarthome/","introduced_date":"2022-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/toyota-smarthome-untrimmed-real-world","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","first_author":"Rui Dai","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Detection","url":"/task/action-detection","datasets_with_task":"/datasets/task/action-detection"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Activity Detection","url":"/task/activity-detection","datasets_with_task":"/datasets/task/activity-detection"}],"languages":[],"variants":["TSU","Toyota Smarthome Dataset","Toyota Smarthome dataset"],"data_loaders":[{"repo":"https://github.com/dairui01/Toyota_Smarthome","url":"https://github.com/dairui01/Toyota_Smarthome","frameworks":[]}],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-classification-on-toyota-smarthome","task":"Action Classification","dataset_variant":"Toyota Smarthome dataset","rows":13,"metrics":["CS","CV1","CV2","Accuracy"],"first_row_in_archive_order":{"model":"π-ViT","paper":"/paper/just-add-p-pose-induced-video-transformers","metrics":{"CS":"72.9","CV1":"55.2","CV2":"64.8"},"code_links":[{"title":"dominickrei/pi-vit","url":"https://github.com/dominickrei/pi-vit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":13,"of":13,"counts":{"papers_with_a_benchmark_row":13,"with_a_code_link":9,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/epam-net-an-efficient-pose-driven-attention","slug":"epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","arxiv_id":"2408.05421","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/just-add-p-pose-induced-video-transformers","slug":"just-add-p-pose-induced-video-transformers","title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","date":"2023-11-30","arxiv_id":"2311.18840","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmnet-a-model-based-multimodal-network-for","slug":"mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/proformer-learning-data-efficient","slug":"proformer-learning-data-efficient","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","date":"2022-02-23","arxiv_id":"2202.11423","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unik-a-unified-framework-for-real-world","slug":"unik-a-unified-framework-for-real-world","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","date":"2021-07-19","arxiv_id":"2107.08580","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-intermediate-representations-for","slug":"adaptive-intermediate-representations-for","title":"Adaptive Intermediate Representations for Video Understanding","date":"2021-04-14","arxiv_id":"2104.07135","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recognizing-actions-in-videos-from-unseen","slug":"recognizing-actions-in-videos-from-unseen","title":"Recognizing Actions in Videos from Unseen Viewpoints","date":"2021-03-30","arxiv_id":"2103.16516","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/assemblenet-assembling-modality","slug":"assemblenet-assembling-modality","title":"AssembleNet++: Assembling Modality Representations via Attention Connections","date":"2020-08-18","arxiv_id":"2008.08072","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vpn-learning-video-pose-embedding-for","slug":"vpn-learning-video-pose-embedding-for","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","date":"2020-07-06","arxiv_id":"2007.03056","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/toyota-smarthome-real-world-activities-of","slug":"toyota-smarthome-real-world-activities-of","title":"Toyota Smarthome: Real-World Activities of Daily Living","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"paper":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":16,"samples_constructed":7,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":12,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}}}},{"paper":"/paper/improved-dense-trajectory-with-cross-streams","slug":"improved-dense-trajectory-with-cross-streams","title":"Improved Dense Trajectory with Cross Streams","date":"2016-04-29","arxiv_id":"1604.08826","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/epam-net-an-efficient-pose-driven-attention","slug":"epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","arxiv_id":"2408.05421","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/just-add-p-pose-induced-video-transformers","slug":"just-add-p-pose-induced-video-transformers","title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","date":"2023-11-30","arxiv_id":"2311.18840","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmnet-a-model-based-multimodal-network-for","slug":"mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/proformer-learning-data-efficient","slug":"proformer-learning-data-efficient","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","date":"2022-02-23","arxiv_id":"2202.11423","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unik-a-unified-framework-for-real-world","slug":"unik-a-unified-framework-for-real-world","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","date":"2021-07-19","arxiv_id":"2107.08580","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-intermediate-representations-for","slug":"adaptive-intermediate-representations-for","title":"Adaptive Intermediate Representations for Video Understanding","date":"2021-04-14","arxiv_id":"2104.07135","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recognizing-actions-in-videos-from-unseen","slug":"recognizing-actions-in-videos-from-unseen","title":"Recognizing Actions in Videos from Unseen Viewpoints","date":"2021-03-30","arxiv_id":"2103.16516","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/assemblenet-assembling-modality","slug":"assemblenet-assembling-modality","title":"AssembleNet++: Assembling Modality Representations via Attention Connections","date":"2020-08-18","arxiv_id":"2008.08072","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vpn-learning-video-pose-embedding-for","slug":"vpn-learning-video-pose-embedding-for","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","date":"2020-07-06","arxiv_id":"2007.03056","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/toyota-smarthome-real-world-activities-of","slug":"toyota-smarthome-real-world-activities-of","title":"Toyota Smarthome: Real-World Activities of Daily Living","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"paper":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":16,"samples_constructed":7,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":12,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}}}},{"paper":"/paper/improved-dense-trajectory-with-cross-streams","slug":"improved-dense-trajectory-with-cross-streams","title":"Improved Dense Trajectory with Cross Streams","date":"2016-04-29","arxiv_id":"1604.08826","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/toyota-smarthome/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/toyota-smarthome/papers/ran/1","json":"/dataset/toyota-smarthome/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":32,"samples_ran":19,"samples_constructed":7,"samples_ran_checked":11,"samples_ran_instrument_failed":8,"samples_unverified":13,"pointer_only_for_licence":11,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"bcd4779254face808665a40ba3097ea741f510219d54ce24ce6d78e280ece53e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}