{"id":"https://openalex.org/W2995849700","doi":null,"title":"CATER: A diagnostic dataset for Compositional Actions & TEmporal Reasoning","display_name":"CATER: A diagnostic dataset for Compositional Actions & TEmporal Reasoning","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995849700","mag":"2995849700"},"language":"en","primary_location":{"id":"mag:2995849700","doi":null,"is_oa":false,"landing_page_url":"http://www.openreview.net/pdf?id=HJgzt2VKPB","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006312307","display_name":"Rohit Girdhar","orcid":"https://orcid.org/0000-0003-2393-6832","observed_orcids":["https://orcid.org/0000-0003-2393-6832"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Girdhar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004353237","display_name":"Deva Ramanan","orcid":"https://orcid.org/0009-0008-9180-8983","observed_orcids":["https://orcid.org/0009-0008-9180-8983"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deva Ramanan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0009-0008-9180-8983","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.8854,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93111639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.014100000262260437,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.6940000057220459},{"id":"https://openalex.org/keywords/spatio-temporal-reasoning","display_name":"spatio-temporal reasoning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/temporal-reasoning","display_name":"temporal reasoning","score":0.7129999995231628},{"id":"https://openalex.org/keywords/synthetic-video","display_name":"synthetic video","score":0.6499999761581421},{"id":"https://openalex.org/keywords/3d-object-rendering","display_name":"3D object rendering","score":0.6510000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571903705596924},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7024373412132263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6799277663230896},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5628552436828613},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4746288061141968},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4366888999938965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4114147424697876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36050552129745483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2630416452884674},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995849700","doi":null,"is_oa":false,"landing_page_url":"http://www.openreview.net/pdf?id=HJgzt2VKPB","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1513100184","https://openalex.org/W1522734439","https://openalex.org/W1591870335","https://openalex.org/W1757796397","https://openalex.org/W1906662973","https://openalex.org/W1942126453","https://openalex.org/W1947481528","https://openalex.org/W1964238623","https://openalex.org/W1981636936","https://openalex.org/W1996703663","https://openalex.org/W2016053056","https://openalex.org/W2019660985","https://openalex.org/W2020163092","https://openalex.org/W2034328688","https://openalex.org/W2064675550","https://openalex.org/W2096621047","https://openalex.org/W2101032778","https://openalex.org/W2105101328","https://openalex.org/W2111078031","https://openalex.org/W2111800993","https://openalex.org/W2116435618","https://openalex.org/W2126574503","https://openalex.org/W2126579184","https://openalex.org/W2128951574","https://openalex.org/W2134266767","https://openalex.org/W2150191218","https://openalex.org/W2156303437","https://openalex.org/W2161484642","https://openalex.org/W2167072892","https://openalex.org/W2167613050","https://openalex.org/W2175640409","https://openalex.org/W2190067570","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2274287116","https://openalex.org/W2335364074","https://openalex.org/W2337252826","https://openalex.org/W2345308174","https://openalex.org/W2362143032","https://openalex.org/W2400532028","https://openalex.org/W2507009361","https://openalex.org/W2511671220","https://openalex.org/W2553594924","https://openalex.org/W2557465155","https://openalex.org/W2559917662","https://openalex.org/W2561715562","https://openalex.org/W2576289912","https://openalex.org/W2578797046","https://openalex.org/W2606982687","https://openalex.org/W2608988379","https://openalex.org/W2615547864","https://openalex.org/W2618799552","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2706729717","https://openalex.org/W2724998899","https://openalex.org/W2742343242","https://openalex.org/W2742764018","https://openalex.org/W2747804831","https://openalex.org/W2760079692","https://openalex.org/W2773514261","https://openalex.org/W2775771349","https://openalex.org/W2776202271","https://openalex.org/W2885380450","https://openalex.org/W2886910176","https://openalex.org/W2895243423","https://openalex.org/W2897857500","https://openalex.org/W2962867954","https://openalex.org/W2962899219","https://openalex.org/W2963076818","https://openalex.org/W2963088756","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963446712","https://openalex.org/W2963499233","https://openalex.org/W2964134613","https://openalex.org/W2970806862","https://openalex.org/W2978723076","https://openalex.org/W2995278527","https://openalex.org/W3100388886"],"related_works":["https://openalex.org/W2980139307","https://openalex.org/W4415540635","https://openalex.org/W7127448947","https://openalex.org/W4404893151","https://openalex.org/W3120048909","https://openalex.org/W4402716268","https://openalex.org/W6945738893","https://openalex.org/W2964111881","https://openalex.org/W7138930316","https://openalex.org/W4412944952"],"abstract_inverted_index":{"Computer":[0],"vision":[1],"has":[2,34],"undergone":[3],"a":[4,85,116,140,146],"dramatic":[5],"revolution":[6],"in":[7,10,77,103],"performance,":[8],"driven":[9],"large":[11],"part":[12],"through":[13],"deep":[14,178],"features":[15],"trained":[16],"on":[17,28],"large-scale":[18],"supervised":[19],"datasets.":[20],"However,":[21],"much":[22],"of":[23,118,129,148,170,175],"these":[24],"improvements":[25],"have":[26,46],"focused":[27],"static":[29],"image":[30],"analysis;":[31],"video":[32,61,86,155,179],"understanding":[33,102],"seen":[35],"rather":[36],"modest":[37],"improvements.":[38],"Even":[39],"though":[40],"new":[41],"datasets":[42,62],"and":[43,70,91,94,97,122,161],"spatiotemporal":[44,101,154],"models":[45],"been":[47],"proposed,":[48],"simple":[49],"frame-by-frame":[50],"classification":[51],"methods":[52],"often":[53],"still":[54],"remain":[55],"competitive.":[56],"We":[57],"posit":[58],"that":[59,73,132],"current":[60],"are":[63],"plagued":[64],"with":[65,88],"implicit":[66],"biases":[67],"over":[68],"scene":[69,95],"object":[71,93,130],"structure":[72],"can":[74],"dwarf":[75],"variations":[76],"temporal":[78],"structure.":[79],"In":[80,136],"this":[81],"work,":[82],"we":[83,165],"build":[84],"dataset":[87],"fully":[89],"observable":[90,160],"controllable":[92],"bias,":[96],"which":[98],"truly":[99],"requires":[100],"order":[104],"to":[105,126,138,151],"be":[106],"solved.":[107],"Our":[108],"dataset,":[109,142],"named":[110],"CATER,":[111,164],"is":[112],"rendered":[113],"synthetically":[114],"using":[115],"library":[117],"standard":[119],"3D":[120],"objects,":[121],"tests":[123],"the":[124,171,176],"ability":[125],"recognize":[127],"compositions":[128],"movements":[131],"require":[133],"long-term":[134],"reasoning.":[135],"addition":[137],"being":[139,158],"challenging":[141],"CATER":[143],"also":[144],"provides":[145],"plethora":[147],"diagnostic":[149],"tools":[150],"analyze":[152],"modern":[153],"architectures":[156],"by":[157],"completely":[159],"controllable.":[162],"Using":[163],"provide":[166],"insights":[167],"into":[168],"some":[169],"most":[172],"recent":[173],"state":[174],"art":[177],"architectures.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}