{"id":"https://openalex.org/W2765906606","doi":"https://doi.org/10.1145/3123266.3123349","title":"Learning Object-Centric Transformation for Video Prediction","display_name":"Learning Object-Centric Transformation for Video Prediction","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2765906606","doi":"https://doi.org/10.1145/3123266.3123349","mag":"2765906606"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th 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/A5034398151","display_name":"Xiongtao Chen","orcid":"https://orcid.org/0000-0002-6349-8737"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiongtao Chen","raw_affiliation_strings":["Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017052768","display_name":"Wenmin Wang","orcid":"https://orcid.org/0000-0003-2664-4413"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenmin Wang","raw_affiliation_strings":["Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084797829","display_name":"Jinzhuo Wang","orcid":"https://orcid.org/0000-0002-9464-4426"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinzhuo Wang","raw_affiliation_strings":["Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044711027","display_name":"Weimian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimian Li","raw_affiliation_strings":["Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034398151"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":0.6371,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.78798669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1503","last_page":"1512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8307284116744995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7793608903884888},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7337567806243896},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6363241672515869},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6254671216011047},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.601425290107727},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5711615085601807},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5460694432258606},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5282889008522034},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.5239368081092834},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5084182620048523},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4470677375793457},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.4363774061203003},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.26330888271331787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307284116744995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7793608903884888},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7337567806243896},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6363241672515869},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6254671216011047},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.601425290107727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5711615085601807},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5460694432258606},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5282889008522034},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.5239368081092834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5084182620048523},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4470677375793457},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.4363774061203003},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26330888271331787},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W603908379","https://openalex.org/W764651262","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1537098388","https://openalex.org/W1568514080","https://openalex.org/W1776042733","https://openalex.org/W1905052409","https://openalex.org/W1930563420","https://openalex.org/W2016053056","https://openalex.org/W2016776918","https://openalex.org/W2090518410","https://openalex.org/W2116435618","https://openalex.org/W2118688707","https://openalex.org/W2119717200","https://openalex.org/W2126574503","https://openalex.org/W2133665775","https://openalex.org/W2145467074","https://openalex.org/W2147527908","https://openalex.org/W2175030374","https://openalex.org/W2179352600","https://openalex.org/W2185953016","https://openalex.org/W2271840356","https://openalex.org/W2414711238","https://openalex.org/W2470142083","https://openalex.org/W2470475590","https://openalex.org/W2591342762","https://openalex.org/W2911273949","https://openalex.org/W2949099979","https://openalex.org/W2952453038","https://openalex.org/W2953133772","https://openalex.org/W2963125871","https://openalex.org/W2963321993","https://openalex.org/W2964132058","https://openalex.org/W3098722327","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W4389249638","https://openalex.org/W855007925","https://openalex.org/W2618671746","https://openalex.org/W2898107007"],"abstract_inverted_index":{"Future":[0],"frame":[1,115],"prediction":[2,90],"for":[3,23,98,187],"video":[4,89,133],"sequences":[5],"is":[6,153],"a":[7,71,86],"challenging":[8],"task":[9],"and":[10,40,166,169,190],"worth":[11],"exploring":[12],"problem":[13],"in":[14,34,42,81,132,155],"computer":[15],"vision.":[16],"Existing":[17],"methods":[18],"often":[19,38,52],"learn":[20],"motion":[21,62,95,186],"information":[22],"the":[24,35,47,56,110,163],"entire":[25,68],"image":[26,69],"to":[27,55,109,128,130,174],"predict":[28],"next":[29,114],"frames.":[30,194],"However,":[31],"different":[32,43,188],"objects":[33,58,107,131,189],"same":[36],"scene":[37],"move":[39],"deform":[41],"ways":[44],"intuitively.":[45],"Considering":[46],"human":[48,79],"visual":[49,103],"system,":[50],"one":[51],"pays":[53],"attention":[54,123],"key":[57,99],"that":[59,92,181],"contain":[60],"crucial":[61],"signals,":[63],"rather":[64],"than":[65],"compress":[66],"an":[67,122],"into":[70],"static":[72],"representation.":[73],"Motivated":[74],"by":[75],"this":[76,82],"property":[77],"of":[78],"perception,":[80],"work,":[83],"we":[84,120],"develop":[85],"novel":[87],"object-centric":[88],"model":[91,161,183],"learns":[93],"local":[94],"transformation":[96],"dynamically":[97],"object":[100],"regions":[101],"with":[102,125],"attention.":[104],"By":[105],"transforming":[106],"iteratively":[108],"original":[111],"input":[112],"frames,":[113],"can":[116,184],"be":[117],"produced.":[118],"Specifically,":[119],"design":[121],"module":[124],"replaceable":[126],"strategies":[127],"attend":[129],"frames":[134,179],"automatically.":[135],"Our":[136],"method":[137],"does":[138],"not":[139],"require":[140],"any":[141],"annotated":[142],"data":[143],"during":[144],"training":[145,152],"procedure.":[146],"To":[147],"produce":[148,191],"sharp":[149],"predictions,":[150],"adversarial":[151],"adopted":[154],"our":[156,160,182],"work.":[157],"We":[158],"evaluate":[159],"on":[162],"Moving":[164],"MNIST":[165],"UCF101":[167],"datasets":[168],"report":[170],"competitive":[171],"results,":[172],"compared":[173],"prior":[175],"methods.":[176],"The":[177],"generated":[178],"demonstrate":[180],"characterize":[185],"plausible":[192],"future":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}