{"id":"https://openalex.org/W2981664267","doi":"https://doi.org/10.1145/3343031.3351094","title":"Watch, Reason and Code","display_name":"Watch, Reason and Code","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981664267","doi":"https://doi.org/10.1145/3343031.3351094","mag":"2981664267"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5028258340","display_name":"Xuguang Duan","orcid":"https://orcid.org/0000-0001-9108-9618"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuguang Duan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-Watson AI Lab, Watson, China"],"affiliations":[{"raw_affiliation_string":"MIT-Watson AI Lab, Watson, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410221","display_name":"Yiwei Zhang","orcid":"https://orcid.org/0000-0003-0140-144X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032642601","display_name":"Wenbing Huang","orcid":"https://orcid.org/0000-0002-2566-4159"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbing Huang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028024287","display_name":"Anton van den Hengel","orcid":"https://orcid.org/0000-0003-3027-8364"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anton van den Hengel","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028258340"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54745703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1543","last_page":"1551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8299297094345093},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.803354024887085},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6737862229347229},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6029726266860962},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5869325995445251},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5792707204818726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5523821711540222},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5113360285758972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46775174140930176},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45283034443855286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38392549753189087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299297094345093},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.803354024887085},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6737862229347229},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6029726266860962},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5869325995445251},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5792707204818726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5523821711540222},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5113360285758972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46775174140930176},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45283034443855286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38392549753189087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3343031.3351094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/129989","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/129989","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dl.acm.org/doi/proceedings/10.1145/3343031","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1732222442","https://openalex.org/W1900913856","https://openalex.org/W2059383863","https://openalex.org/W2139501017","https://openalex.org/W2147615062","https://openalex.org/W2165005075","https://openalex.org/W2172207578","https://openalex.org/W2425121537","https://openalex.org/W2512435841","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2584992898","https://openalex.org/W2593390416","https://openalex.org/W2607119937","https://openalex.org/W2798271879","https://openalex.org/W2952186347","https://openalex.org/W2963220331","https://openalex.org/W2963576560","https://openalex.org/W2963907629","https://openalex.org/W2963916161"],"related_works":["https://openalex.org/W2350278424","https://openalex.org/W2071432835","https://openalex.org/W4239401009","https://openalex.org/W4234371507","https://openalex.org/W1628824497","https://openalex.org/W4299534542","https://openalex.org/W2053441600","https://openalex.org/W1990401748","https://openalex.org/W2047586841","https://openalex.org/W2141018266"],"abstract_inverted_index":{"Humans":[0],"have":[1],"a":[2,16,53,61,74,84,108,113,121,131,149,178],"surprising":[3],"capacity":[4,51],"to":[5,29,33,47,64,90,129],"induce":[6],"general":[7,42],"rules":[8,20],"that":[9,67,87,124,171],"describe":[10,68],"the":[11,37,49,69,100,125,158,175],"specific":[12],"actions":[13],"portrayed":[14],"in":[15,36,40,73,163],"video":[17,38,77,85],"sequence.":[18],"The":[19,79,94,117],"learned":[21],"through":[22],"this":[23,57],"kind":[24],"of":[25,76,160,180],"process":[26,70],"allow":[27],"us":[28],"achieve":[30,48,174],"similar":[31],"goals":[32],"those":[34],"shown":[35],"but":[39],"more":[41],"circumstances.":[43],"Enabling":[44],"an":[45],"agent":[46],"same":[50],"represents":[52],"significant":[54],"challenge.":[55],"In":[56],"paper,":[58],"we":[59,172],"propose":[60],"Watch-Reason-Code(WRC)":[62],"model":[63,162],"synthesise":[65],"programs":[66],"carried":[71],"out":[72],"set":[75],"sequences.":[78],"'watch'":[80],"stage":[81,96,119],"is":[82,120],"simply":[83],"encoder":[86],"encodes":[88],"videos":[89,105],"multiple":[91,103],"feature":[92,110],"vectors.":[93],"'reason'":[95],"takes":[97],"as":[98],"input":[99],"features":[101],"from":[102],"diverse":[104],"and":[106,139,147,153],"generates":[107],"compact":[109],"representation":[111],"via":[112],"novel":[114],"deviation-pooling":[115],"method.":[116],"'code'":[118],"multi-sound":[122],"decoder":[123],"first":[126],"step":[127],"leverages":[128],"generate":[130,148],"draft":[132],"program":[133],"layout":[134],"with":[135],"possible":[136],"useful":[137],"statements":[138],"perceptions.":[140],"Further":[141],"steps":[142],"then":[143],"take":[144],"these":[145],"outputs":[146],"fully":[150],"structured,":[151],"compile-able":[152],"executable":[154],"program.":[155],"We":[156],"evaluate":[157],"effectiveness":[159],"our":[161],"two":[164],"video-to-program":[165],"synthesis":[166],"environments,":[167],"Karel":[168],"andVizDoom,":[169],"showing":[170],"can":[173],"state-of-the-art":[176],"under":[177],"variety":[179],"settings.":[181]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}