{"id":"https://openalex.org/W4415709427","doi":"https://doi.org/10.1109/icme59968.2025.11209460","title":"MotionFlow: Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation","display_name":"MotionFlow: Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709427","doi":"https://doi.org/10.1109/icme59968.2025.11209460"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5014108776","display_name":"Ge Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Lei","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342213","display_name":"Chi Wang","orcid":"https://orcid.org/0000-0002-4751-8187"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747441","display_name":"Yikai Wang","orcid":"https://orcid.org/0000-0003-1341-6235"},"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":"Yikai Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869288","display_name":"Hong Li","orcid":"https://orcid.org/0000-0002-5944-7160"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Li","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631945","display_name":"Ying Song","orcid":"https://orcid.org/0000-0003-4813-0245"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Song","raw_affiliation_strings":["Zhejiang Gongshang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110564480","display_name":"Weiwei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Xu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27356376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7376000285148621,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7376000285148621,"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":0.05660000070929527,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.049800001084804535,"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/trajectory","display_name":"Trajectory","score":0.6937000155448914},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6488000154495239},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6324999928474426},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/camera-auto-calibration","display_name":"Camera auto-calibration","score":0.5042999982833862},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4693000018596649},{"id":"https://openalex.org/keywords/camera-resectioning","display_name":"Camera resectioning","score":0.44179999828338623},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4284000098705292}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.77920001745224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7771999835968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265999913215637},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6937000155448914},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C94816000","wikidata":"https://www.wikidata.org/wiki/Q5026006","display_name":"Camera auto-calibration","level":3,"score":0.5042999982833862},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.40459999442100525},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2778852477","wikidata":"https://www.wikidata.org/wiki/Q313614","display_name":"Video camera","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.2556999921798706},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":19,"referenced_works":["https://openalex.org/W1745334888","https://openalex.org/W2471962767","https://openalex.org/W3159481202","https://openalex.org/W4312369807","https://openalex.org/W4386066475","https://openalex.org/W4386076027","https://openalex.org/W4386076323","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4391622623","https://openalex.org/W4393148714","https://openalex.org/W4400573519","https://openalex.org/W4400582084","https://openalex.org/W4402753851","https://openalex.org/W4402775760","https://openalex.org/W4402816534","https://openalex.org/W4402951568","https://openalex.org/W4403003238","https://openalex.org/W4403021266"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"videos":[1],"guided":[2],"by":[3,134],"camera":[4,40,56,88,117],"trajectories":[5],"poses":[6],"significant":[7],"challenges":[8],"in":[9,83],"achieving":[10],"consistency":[11,122],"and":[12,41,58,61],"generalizability,":[13],"particularly":[14],"when":[15],"active":[16],"objects":[17],"are":[18,99],"present.":[19],"Existing":[20],"approaches":[21],"often":[22],"attempt":[23],"to":[24,32,85,106],"learn":[25],"object":[26,59,97],"motions":[27],"separately,":[28],"which":[29],"may":[30],"lead":[31],"confusion":[33],"regarding":[34],"the":[35,39,42,65,69,86,108,115,121],"relative":[36],"motion":[37,67,81],"between":[38],"objects.":[43],"To":[44],"address":[45],"this":[46],"challenge,":[47],"we":[48,77],"propose":[49],"a":[50,73,135],"novel":[51],"approach":[52],"that":[53,111,128],"integrates":[54],"both":[55],"trajectory":[57,118],"semantics":[60],"converts":[62],"them":[63],"into":[64,102],"reference":[66,80],"of":[68,123],"corresponding":[70],"pixels.":[71],"Utilizing":[72],"stable":[74],"diffusion":[75],"network,":[76],"effectively":[78],"extract":[79],"maps":[82],"relation":[84],"specified":[87],"trajectory.":[89],"These":[90],"maps,":[91],"along":[92],"with":[93],"an":[94,103],"extracted":[95],"semantic":[96],"prior,":[98],"then":[100],"fed":[101],"image-to-video":[104],"network":[105],"generate":[107],"desired":[109],"video":[110],"can":[112],"accurately":[113],"follow":[114],"designated":[116],"while":[119],"maintaining":[120],"object.":[124],"Extensive":[125],"experiments":[126],"verify":[127],"our":[129],"model":[130],"outperforms":[131],"SOTA":[132],"methods":[133],"large":[136],"margin.":[137],"Project":[138],"Page:":[139],"https://yu-shaonian.github.io/MotionFlow/":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}