{"id":"https://openalex.org/W4308235904","doi":"https://doi.org/10.1109/icip46576.2022.9897483","title":"Multi-Frame Video Prediction with Learnable Motion Encodings","display_name":"Multi-Frame Video Prediction with Learnable Motion Encodings","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308235904","doi":"https://doi.org/10.1109/icip46576.2022.9897483"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897483","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5012164804","display_name":"Rakesh Jasti","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Jasti","raw_affiliation_strings":["UC Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085870393","display_name":"Varun Jampani","orcid":"https://orcid.org/0000-0002-1508-6498"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varun Jampani","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101440839","display_name":"Deqing Sun","orcid":"https://orcid.org/0000-0003-0329-0456"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deqing Sun","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["UC Merced","Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Merced","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67979862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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/T11105","display_name":"Advanced Image Processing Techniques","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/T11019","display_name":"Image Enhancement Techniques","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":0.7486653327941895},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6953949928283691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6663519740104675},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5993500351905823},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5937921404838562},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5391931533813477},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5339148640632629},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5087936520576477},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.478362500667572},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.47671622037887573},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.45076286792755127},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.39810043573379517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.186146080493927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486653327941895},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6953949928283691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6663519740104675},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5993500351905823},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5937921404838562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5391931533813477},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5339148640632629},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5087936520576477},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.478362500667572},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.47671622037887573},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.45076286792755127},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.39810043573379517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.186146080493927},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897483","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W764651262","https://openalex.org/W1677182931","https://openalex.org/W1901129140","https://openalex.org/W1951289974","https://openalex.org/W2016776918","https://openalex.org/W2031454541","https://openalex.org/W2133665775","https://openalex.org/W2395611524","https://openalex.org/W2535388113","https://openalex.org/W2560474170","https://openalex.org/W2575671312","https://openalex.org/W2883429621","https://openalex.org/W2891942975","https://openalex.org/W2894961607","https://openalex.org/W2911273949","https://openalex.org/W2962914239","https://openalex.org/W2963302737","https://openalex.org/W2963782415","https://openalex.org/W2964254867","https://openalex.org/W2989708447","https://openalex.org/W3015879326","https://openalex.org/W3094891242","https://openalex.org/W6600983433","https://openalex.org/W6631190155","https://openalex.org/W6691096134","https://openalex.org/W6713563955","https://openalex.org/W6738465933","https://openalex.org/W6745499552","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2002497870","https://openalex.org/W2120864667","https://openalex.org/W2366173767","https://openalex.org/W2890140430","https://openalex.org/W2120898383","https://openalex.org/W1999265669","https://openalex.org/W2168627807","https://openalex.org/W1579940903","https://openalex.org/W2140116745","https://openalex.org/W2100145287"],"abstract_inverted_index":{"Predicting":[0],"multiple":[1],"future":[2,49,85,104,148],"frames":[3,62,87],"from":[4],"a":[5,9,45,75,89,100,120],"given":[6],"video":[7,36,86],"is":[8],"challenging":[10],"problem":[11],"due":[12],"to":[13,122,134,142],"several":[14,161],"factors":[15],"such":[16],"as":[17],"changing":[18],"camera,":[19],"dynamically":[20],"moving":[21],"objects,":[22],"occlusions,":[23],"etc.":[24],"While":[25],"recent":[26],"deep":[27],"learning":[28],"methods":[29,40],"have":[30],"made":[31],"significant":[32],"progress":[33],"on":[34,151],"the":[35,42,60,94,124,166,179,187,193],"prediction":[37,169,177],"problem,":[38],"most":[39],"predict":[41,80,123,143],"immediate":[43],"or":[44,67,107,175],"fixed":[46,101],"number":[47,83,102,146],"of":[48,84,97,103,147],"frames.":[50,149],"To":[51],"obtain":[52],"longer-term":[53],"frame":[54,168],"predictions,":[55],"existing":[56],"techniques":[57,163,189],"usually":[58],"process":[59,192],"predicted":[61],"iteratively,":[63],"resulting":[64],"in":[65],"blurry":[66],"inconsistent":[68],"predictions.":[69,194],"In":[70],"this":[71],"work,":[72],"we":[73,109],"present":[74],"new":[76],"approach":[77,157],"that":[78,155,190],"can":[79,130],"an":[81,144],"arbitrary":[82,135,145],"with":[88],"single":[90],"forward":[91],"pass":[92],"through":[93],"network.":[95],"Instead":[96],"directly":[98],"predicting":[99],"optical":[105],"flows":[106],"frames,":[108],"learn":[110],"temporal":[111,115],"motion":[112,116,128],"encodings,":[113],"i.e.,":[114],"basis":[117,129],"vectors":[118],"and":[119],"network":[121],"coefficients.":[125],"The":[126],"learned":[127],"be":[131],"easily":[132],"extended":[133],"length":[136],"at":[137],"inference":[138],"time,":[139],"enabling":[140],"us":[141],"Experiments":[150],"benchmark":[152],"datasets":[153],"show":[154],"our":[156],"performs":[158],"favorably":[159],"against":[160],"competitive":[162],"even":[164],"for":[165],"next":[167],"setting.":[170],"When":[171],"evaluated":[172],"under":[173],"5-frame":[174],"10-frame":[176],"settings,":[178],"proposed":[180],"method":[181],"achieves":[182],"higher":[183],"performance":[184],"gains":[185],"over":[186],"state-of-the-art":[188],"iteratively":[191]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}