{"id":"https://openalex.org/W7138031090","doi":"https://doi.org/10.1609/aaai.v40i14.38125","title":"STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification","display_name":"STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138031090","doi":"https://doi.org/10.1609/aaai.v40i14.38125"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38125","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38125","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38125/42087","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38125/42087","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124804896","display_name":"Xingguo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingguo Xu","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129676913","display_name":"Zhanyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Liu","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672877","display_name":"Weixiang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiang Zhou","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017091175","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0002-5435-8863"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuansheng Gao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716947","display_name":"Junjie Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Cao","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678938","display_name":"Yuhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["School of Future Technology, Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080571980","display_name":"Jixiang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixiang Luo","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129686490","display_name":"Dell Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5124804896"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31696429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11433","last_page":"11441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5339000225067139,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5339000225067139,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19470000267028809,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05689999833703041,"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/hypergraph","display_name":"Hypergraph","score":0.7384999990463257},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6531000137329102},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6456000208854675},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5719000101089478},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4970000088214874},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40560001134872437}],"concepts":[{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.7384999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73089998960495},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6531000137329102},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38125","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38125","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38125/42087","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38125","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38125","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38125/42087","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7760889530181885}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2316792475","display_name":null,"funder_award_id":"62362051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G779969207","display_name":null,"funder_award_id":"6236205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138031090.pdf","grobid_xml":"https://content.openalex.org/works/W7138031090.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"object":[1],"Re-Identification":[2],"(ReID)":[3],"aims":[4],"to":[5,12,32,68,95,117],"exploit":[6],"complementary":[7],"information":[8],"from":[9],"different":[10],"modalities":[11,116],"retrieve":[13],"specific":[14],"objects.":[15],"However,":[16],"existing":[17],"methods":[18],"often":[19],"rely":[20],"on":[21,124],"hard":[22],"token":[23],"filtering":[24],"or":[25],"simple":[26],"fusion":[27],"strategies,":[28],"which":[29],"can":[30],"lead":[31],"the":[33,133],"loss":[34],"of":[35,55,137],"discriminative":[36],"cues":[37],"and":[38,72,90,98,130,135],"increased":[39],"background":[40,74],"interference.":[41],"To":[42],"address":[43],"these":[44],"challenges,":[45],"we":[46],"propose":[47],"STMI,":[48],"a":[49,112],"novel":[50],"multi-modal":[51,143],"learning":[52],"framework":[53,141],"consisting":[54],"three":[56],"key":[57],"components:":[58],"(1)":[59],"Segmentation-Guided":[60],"Feature":[61],"Modulation":[62],"(SFM)":[63],"module":[64,85,110],"leverages":[65],"SAM-generated":[66],"masks":[67],"enhance":[69],"foreground":[70],"representations":[71,100],"suppress":[73],"noise":[75],"through":[76],"learnable":[77,87],"attention":[78],"modulation;":[79],"(2)":[80],"Semantic":[81],"Token":[82],"Reallocation":[83],"(STR)":[84],"employs":[86],"query":[88],"tokens":[89],"an":[91],"adaptive":[92],"reallocation":[93],"mechanism":[94],"extract":[96],"compact":[97],"informative":[99],"without":[101],"discarding":[102],"any":[103],"tokens;":[104],"(3)":[105],"Cross-Modal":[106],"Hypergraph":[107],"Interaction":[108],"(CHI)":[109],"constructs":[111],"unified":[113],"hypergraph":[114],"across":[115],"capture":[118],"high-order":[119],"semantic":[120],"relationships.":[121],"Extensive":[122],"experiments":[123],"public":[125],"benchmarks":[126],"(i.e.,":[127],"RGBNT201,":[128],"RGBNT100,":[129],"MSVR310)":[131],"demonstrate":[132],"effectiveness":[134],"robustness":[136],"our":[138],"proposed":[139],"STMI":[140],"in":[142],"ReID":[144],"scenarios.":[145]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}