{"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/cater","name":"CATER","full_name":null,"description_markdown":"Rendered synthetically using a library of standard 3D objects, and tests the ability to recognize compositions of object movements that require long-term reasoning.\r\n\r\nSource: [CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning](/paper/cater-a-diagnostic-dataset-for-compositional)\r\n\r\nImage Source: [CATER](https://rohitgirdhar.github.io/CATER/)","description_withheld":null,"homepage":"https://rohitgirdhar.github.io/CATER/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/cater-a-diagnostic-dataset-for-compositional","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","first_author":"Rohit Girdhar","url":null},"license":{"name":"Apache License 2.0","url":"https://github.com/rohitgirdhar/CATER/blob/master/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Video Object Tracking","url":"/task/video-object-tracking","datasets_with_task":"/datasets/task/video-object-tracking"},{"name":"Atomic action recognition","url":"/task/atomic-action-recognition","datasets_with_task":"/datasets/task/atomic-action-recognition"},{"name":"Composite action recognition","url":"/task/composite-action-recognition","datasets_with_task":"/datasets/task/composite-action-recognition"}],"languages":[],"variants":["CATER"],"data_loaders":[],"num_papers_in_archive":51,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-object-tracking-on-cater","task":"Video Object Tracking","dataset_variant":"CATER","rows":7,"metrics":["Top 1 Accuracy","L1","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"Loci","paper":"/paper/learning-what-and-where-unsupervised","metrics":{"L1":"0.14","Top 1 Accuracy":"90.7","Top 5 Accuracy":"98.5"},"code_links":[{"title":"CognitiveModeling/Loci","url":"https://github.com/CognitiveModeling/Loci"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/atomic-action-recognition-on-cater","task":"Atomic action recognition","dataset_variant":"CATER","rows":4,"metrics":["Average-mAP"],"first_row_in_archive_order":{"model":"SCI3D","paper":"/paper/deep-set-conditioned-latent-representations-1","metrics":{"Average-mAP":"96.77"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/composite-action-recognition-on-cater","task":"Composite action recognition","dataset_variant":"CATER","rows":4,"metrics":["Average-mAP"],"first_row_in_archive_order":{"model":"Single stream SCI3D","paper":"/paper/deep-set-conditioned-latent-representations-1","metrics":{"Average-mAP":"69.76"},"code_links":[]},"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":8,"of":8,"counts":{"papers_with_a_benchmark_row":8,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":8,"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/deep-set-conditioned-latent-representations-1","slug":"deep-set-conditioned-latent-representations-1","title":"Deep set conditioned latent representations for action recognition","date":"2022-12-21","arxiv_id":"2212.11030","rows_on_this_dataset":8,"code_links":0,"syntology":null},{"paper":"/paper/learning-what-and-where-unsupervised","slug":"learning-what-and-where-unsupervised","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","date":"2022-05-26","arxiv_id":"2205.13349","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tfcnet-temporal-fully-connected-networks-for","slug":"tfcnet-temporal-fully-connected-networks-for","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","date":"2022-03-11","arxiv_id":"2203.05928","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/inferno-inferring-object-centric-3d-scene","slug":"inferno-inferring-object-centric-3d-scene","title":"INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hopper-multi-hop-transformer-for-1","slug":"hopper-multi-hop-transformer-for-1","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","date":"2021-03-19","arxiv_id":"2103.10574","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/object-based-attention-for-spatio-temporal","slug":"object-based-attention-for-spatio-temporal","title":"Attention over learned object embeddings enables complex visual reasoning","date":"2020-12-15","arxiv_id":"2012.08508","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-object-permanence-from-video","slug":"learning-object-permanence-from-video","title":"Learning Object Permanence from Video","date":"2020-03-23","arxiv_id":"2003.10469","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-object-permanence-from-video#ran","syntology_url":"https://syntology.ai/paper/2003.10469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10469"}}}},{"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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/deep-set-conditioned-latent-representations-1","slug":"deep-set-conditioned-latent-representations-1","title":"Deep set conditioned latent representations for action recognition","date":"2022-12-21","arxiv_id":"2212.11030","rows_on_this_dataset":8,"code_links":0,"syntology":null},{"paper":"/paper/learning-what-and-where-unsupervised","slug":"learning-what-and-where-unsupervised","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","date":"2022-05-26","arxiv_id":"2205.13349","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tfcnet-temporal-fully-connected-networks-for","slug":"tfcnet-temporal-fully-connected-networks-for","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","date":"2022-03-11","arxiv_id":"2203.05928","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/inferno-inferring-object-centric-3d-scene","slug":"inferno-inferring-object-centric-3d-scene","title":"INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hopper-multi-hop-transformer-for-1","slug":"hopper-multi-hop-transformer-for-1","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","date":"2021-03-19","arxiv_id":"2103.10574","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/object-based-attention-for-spatio-temporal","slug":"object-based-attention-for-spatio-temporal","title":"Attention over learned object embeddings enables complex visual reasoning","date":"2020-12-15","arxiv_id":"2012.08508","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-object-permanence-from-video","slug":"learning-object-permanence-from-video","title":"Learning Object Permanence from Video","date":"2020-03-23","arxiv_id":"2003.10469","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-object-permanence-from-video#ran","syntology_url":"https://syntology.ai/paper/2003.10469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10469"}}}},{"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"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/cater/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/cater/papers/ran/1","json":"/dataset/cater/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":18,"samples_constructed":7,"samples_ran_checked":12,"samples_ran_instrument_failed":6,"samples_unverified":14,"pointer_only_for_licence":7,"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":"404eda5d41acdd379c56ebcd5349716737fc0e665cc092e54e136b0a26739b78","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}