{"id":"https://openalex.org/W2892364636","doi":"https://doi.org/10.1145/3240876.3240886","title":"Object-oriented video prediction with pixel-level attention","display_name":"Object-oriented video prediction with pixel-level attention","publication_year":2018,"publication_date":"2018-08-17","ids":{"openalex":"https://openalex.org/W2892364636","doi":"https://doi.org/10.1145/3240876.3240886","mag":"2892364636"},"language":"en","primary_location":{"id":"doi:10.1145/3240876.3240886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240876.3240886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Internet Multimedia Computing and Service","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066614468","display_name":"Siyuan Wu","orcid":"https://orcid.org/0000-0003-1487-1571"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119247506","display_name":"Qinyu Li","orcid":"https://orcid.org/0000-0003-0862-4451"},"institutions":[{"id":"https://openalex.org/I4210140336","display_name":"Lanzhou City University","ror":"https://ror.org/03cd4ja39","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210140336"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Qinyu Li","raw_affiliation_strings":["Lanzhou City University, Gansu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou City University, Gansu, China","institution_ids":["https://openalex.org/I4210140336","https://openalex.org/I6469544"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/pixel","display_name":"Pixel","score":0.8668680191040039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441272974014282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7701926231384277},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6870424151420593},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.636723518371582},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5730004906654358}],"concepts":[{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.8668680191040039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441272974014282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7701926231384277},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6870424151420593},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.636723518371582},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5730004906654358},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240876.3240886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240876.3240886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Internet Multimedia Computing and Service","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1850742715","https://openalex.org/W2101032778","https://openalex.org/W2118688707","https://openalex.org/W2271840356","https://openalex.org/W2400532028","https://openalex.org/W2950304420","https://openalex.org/W2953118818","https://openalex.org/W2963125871"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"It":[0],"is":[1,29,55,83],"really":[2],"challenging":[3],"to":[4,47,60,85,104,116,121],"predict":[5,76],"future":[6,77],"video":[7,24,78,87,111],"contents":[8],"which":[9],"can":[10],"be":[11],"partly":[12],"achieved":[13],"by":[14,90],"learning":[15],"from":[16,67],"tons":[17],"of":[18,36,64,95,125],"videos":[19],"automatically.":[20],"Among":[21],"the":[22,62,68,123,126],"known":[23],"prediction":[25,28,34,53,88,93,101,112],"approaches,":[26],"pixel-level":[27,72],"much":[30],"harder":[31],"than":[32],"label-level":[33],"because":[35],"its":[37],"dense":[38],"characteristics.":[39],"Unlike":[40],"other":[41],"researches":[42],"viewing":[43],"pixels":[44],"as":[45],"units":[46],"make":[48],"pixel":[49],"prediction,":[50],"a":[51,98],"novel":[52],"method":[54,82],"proposed":[56,81,127],"in":[57,97],"this":[58],"work":[59],"learn":[61],"movement":[63],"visual":[65],"objects":[66],"previous":[69],"frames":[70],"via":[71],"attention":[73],"and":[74],"thus":[75],"frames.":[79],"The":[80],"able":[84],"promote":[86],"performances":[89],"making":[91],"object-oriented":[92],"instead":[94],"pixel-oriented":[96],"long-term":[99],"frame":[100],"manner,":[102],"up":[103],"around":[105],"one":[106],"second.":[107],"Two":[108],"large":[109],"real-world":[110],"datasets":[113],"are":[114],"employed":[115],"carry":[117],"out":[118],"comparative":[119],"experiments":[120],"demonstrate":[122],"effectiveness":[124],"method.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}