{"id":"https://openalex.org/W4413144409","doi":"https://doi.org/10.1109/cvpr52734.2025.00158","title":"ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling","display_name":"ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144409","doi":"https://doi.org/10.1109/cvpr52734.2025.00158"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5044126585","display_name":"Zikang Zhou","orcid":"https://orcid.org/0000-0001-9472-4162"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zikang Zhou","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hengjian Zhou","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":"Hengjian Zhou","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/A5101536207","display_name":"Haibo Hu","orcid":"https://orcid.org/0000-0001-8442-5222"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haibo Hu","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040383374","display_name":"Zihao Wen","orcid":"https://orcid.org/0009-0004-3740-5412"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zihao Wen","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356291","display_name":"Jianping Wang","orcid":"https://orcid.org/0000-0002-9318-1482"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianping Wang","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048205934","display_name":"Yung\u2010Hui Li","orcid":"https://orcid.org/0000-0002-0475-3689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Hui Li","raw_affiliation_strings":["Hon Hai Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hon Hai Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011527710","display_name":"Yu-Kai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Kai Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0351,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96697508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1612","last_page":"1621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9943000078201294,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9936000108718872,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478692531585693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5594024062156677},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4675558805465698},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4524969458580017},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32001394033432007},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.09695613384246826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478692531585693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594024062156677},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4675558805465698},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4524969458580017},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32001394033432007},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.09695613384246826}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Anticipating":[0],"the":[1,7,24,34,71,102,119,129,136,143,153,160,175,198,210],"multimodality":[2],"of":[3,26,105,146,177,200],"future":[4,211],"events":[5],"lays":[6],"foundation":[8],"for":[9,17],"safe":[10],"autonomous":[11],"driving.":[12],"However,":[13],"multimodal":[14,27,93,178],"motion":[15,115,190],"prediction":[16,94,168,191],"traffic":[18],"agents":[19],"has":[20],"been":[21],"clouded":[22],"by":[23,59,123],"lack":[25],"ground":[28],"truth.":[29],"Existing":[30],"works":[31],"predominantly":[32],"adopt":[33],"winner-take-all":[35],"training":[36,156],"strategy":[37,157],"to":[38,69,88,117,138,158],"tackle":[39],"this":[40],"challenge,":[41],"yet":[42],"still":[43],"suffer":[44],"from":[45],"limited":[46],"trajectory":[47,62,82,183],"diversity":[48,176],"and":[49,80,133],"uncalibrated":[50],"mode":[51,121,148,167,201],"confidence.":[52],"While":[53],"some":[54],"approaches":[55],"address":[56],"these":[57],"limitations":[58],"generating":[60],"excessive":[61],"candidates,":[63],"they":[64],"necessitate":[65],"a":[66,75,91],"postprocessing":[67],"stage":[68],"identify":[70],"most":[72],"representative":[73],"modes,":[74],"process":[76],"lacking":[77],"universal":[78],"principles":[79],"compromising":[81],"accuracy.":[83],"We":[84],"are":[85],"thus":[86],"motivated":[87],"introduce":[89],"ModeSeq,":[90],"new":[92],"paradigm":[95],"that":[96],"models":[97],"modes":[98,132,208],"as":[99],"sequences.":[100],"Unlike":[101],"common":[103],"practice":[104],"decoding":[106],"multiple":[107],"plausible":[108],"trajectories":[109,161],"in":[110,186],"one":[111],"shot,":[112],"ModeSeq":[113,172,194],"requires":[114],"decoders":[116],"infer":[118],"next":[120],"step":[122],"step,":[124],"thereby":[125],"more":[126,206],"explicitly":[127],"capturing":[128],"correlation":[130],"between":[131],"significantly":[134],"enhancing":[135],"ability":[137],"reason":[139],"about":[140],"multimodality.":[141],"Leveraging":[142],"inductive":[144],"bias":[145],"sequential":[147],"prediction,":[149],"we":[150],"also":[151],"propose":[152],"EarlyMatch-Take-All":[154],"(EMTA)":[155],"diversify":[159],"further.":[162],"Without":[163],"relying":[164],"on":[165,189],"dense":[166],"or":[169],"heuristic":[170],"post-processing,":[171],"considerably":[173],"improves":[174],"output":[179],"while":[180],"attaining":[181],"satisfactory":[182],"accuracy,":[184],"resulting":[185],"balanced":[187],"performance":[188],"benchmarks.":[192],"Moreover,":[193],"naturally":[195],"emerges":[196],"with":[197],"capability":[199],"extrapolation,":[202],"which":[203],"supports":[204],"forecasting":[205],"behavior":[207],"when":[209],"is":[212],"highly":[213],"uncertain.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}