{"id":"https://openalex.org/W4413144338","doi":"https://doi.org/10.1109/cvpr52734.2025.02118","title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","display_name":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144338","doi":"https://doi.org/10.1109/cvpr52734.2025.02118"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02118","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":"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/A5062961322","display_name":"Haonan Han","orcid":null},"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":"Haonan Han","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374743","display_name":"Xiaoguang Wu","orcid":"https://orcid.org/0009-0002-2814-2193"},"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":"Xiangzuo Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100557582","display_name":"Huan Liao","orcid":null},"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":"Huan Liao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145225","display_name":"Zunnan Xu","orcid":null},"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":"Zunnan Xu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065924742","display_name":"Zhongyuan Hu","orcid":null},"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":"Zhongyuan Hu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419739","display_name":"Ronghui Li","orcid":"https://orcid.org/0000-0001-7703-9315"},"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":"Ronghui Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002576518","display_name":"Yachao Zhang","orcid":"https://orcid.org/0000-0002-4468-6142"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachao Zhang","raw_affiliation_strings":["Xiamen University,School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"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":"Xiu Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"22746","last_page":"22755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.7730000019073486,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.7730000019073486,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6758999824523926,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5844895839691162},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.583371639251709},{"id":"https://openalex.org/keywords/atom","display_name":"Atom (system on chip)","score":0.5759565234184265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47257792949676514},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3047977387905121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2396969497203827},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1255623996257782},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.10956209897994995}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5844895839691162},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.583371639251709},{"id":"https://openalex.org/C58312451","wikidata":"https://www.wikidata.org/wiki/Q4817200","display_name":"Atom (system on chip)","level":2,"score":0.5759565234184265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47257792949676514},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3047977387905121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2396969497203827},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1255623996257782},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.10956209897994995}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02118","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2935759653","https://openalex.org/W3105167352","https://openalex.org/W54078636","https://openalex.org/W2954470139","https://openalex.org/W1501425562","https://openalex.org/W2902782467","https://openalex.org/W3084825885"],"abstract_inverted_index":{"Recently,":[0],"text-to-motion":[1,123,144],"models":[2],"have":[3],"opened":[4],"new":[5],"possibilities":[6],"for":[7,102,115],"creating":[8],"realistic":[9],"human":[10],"motion":[11,19,38,54,104],"with":[12,21,81],"greater":[13],"efficiency":[14],"and":[15,36,55,90,112],"flexibility.":[16],"However,":[17],"aligning":[18],"generation":[20],"event-level":[22,78,140],"textual":[23,34,79],"descriptions":[24],"presents":[25],"unique":[26],"challenges":[27],"due":[28],"to":[29],"the":[30,50,86,139],"complex":[31],"relationship":[32,89],"between":[33,52],"prompts":[35,57,80],"desired":[37],"outcomes.":[39],"To":[40],"address":[41],"this,":[42],"we":[43,69,95,119],"introduce":[44],"AToM,":[45],"a":[46,71,97],"framework":[47],"that":[48,99,135],"enhances":[49],"alignment":[51,141],"generated":[53,82],"text":[56],"by":[58,129],"leveraging":[59],"reward":[60],"from":[61],"GPT-4Vision.":[62],"AToM":[63,136],"comprises":[64],"three":[65,75],"main":[66],"stages:":[67],"Firstly,":[68],"construct":[70],"dataset":[72],"MotionPreferthat":[73],"pairs":[74],"types":[76],"of":[77,92,143],"motions,":[83],"which":[84],"cover":[85],"integrity,":[87],"temporal":[88],"frequency":[91],"motion.":[93],"Secondly,":[94],"design":[96],"paradigm":[98],"utilizes":[100],"GPT-4Vision":[101],"detailed":[103],"annotation,":[105],"including":[106],"visual":[107],"data":[108],"formatting,":[109],"task-specific":[110],"instructions":[111],"scoring":[113],"rules":[114],"each":[116],"sub-task.":[117],"Finally,":[118],"fine-tune":[120],"an":[121],"existing":[122],"model":[124],"using":[125],"reinforcement":[126],"learning":[127],"guided":[128],"this":[130],"paradigm.":[131],"Experimental":[132],"results":[133],"demonstrate":[134],"significantly":[137],"improves":[138],"quality":[142],"generation.":[145],"Project":[146],"page":[147],"is":[148],"available":[149],"at":[150],"https://atom-motion.github.io/.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
