{"id":"https://openalex.org/W4416965715","doi":"https://doi.org/10.1109/tcsvt.2025.3639574","title":"Constituency-Tree-Induced Vision\u2013Language Alignment for Multimodal Large Language Models","display_name":"Constituency-Tree-Induced Vision\u2013Language Alignment for Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416965715","doi":"https://doi.org/10.1109/tcsvt.2025.3639574"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3639574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3639574","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5004587572","display_name":"Yingchen Zhai","orcid":"https://orcid.org/0000-0002-7980-7901"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchen Zhai","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-7980-7901","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054900679","display_name":"Ning Xu","orcid":"https://orcid.org/0000-0002-7526-4356"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-7526-4356","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019994406","display_name":"Hongshuo Tian","orcid":"https://orcid.org/0000-0001-7635-0961"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongshuo Tian","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7635-0961","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063699066","display_name":"Bolun Zheng","orcid":"https://orcid.org/0000-0001-8788-1725"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolun Zheng","raw_affiliation_strings":["Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8788-1725","affiliations":[{"raw_affiliation_string":"Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054311881","display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1204-0512","affiliations":[{"raw_affiliation_string":"Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120582701","display_name":"Jinbo Cao","orcid":"https://orcid.org/0009-0003-5037-6989"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbo Cao","raw_affiliation_strings":["30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0003-5037-6989","affiliations":[{"raw_affiliation_string":"30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062258244","display_name":"Rongbao Kang","orcid":"https://orcid.org/0000-0001-8487-8520"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongbao Kang","raw_affiliation_strings":["30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-8487-8520","affiliations":[{"raw_affiliation_string":"30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5755-9145","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.28611014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"5384","last_page":"5397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9763000011444092,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9763000011444092,"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":0.002899999963119626,"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/T10028","display_name":"Topic Modeling","score":0.0026000000070780516,"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/parsing","display_name":"Parsing","score":0.6173999905586243},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5619999766349792},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5461000204086304},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.47029998898506165},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42289999127388},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3846000134944916},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.36239999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215000033378601},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5548999905586243},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.527899980545044},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3639574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3639574","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G173205433","display_name":null,"funder_award_id":"U21b2024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G541546930","display_name":null,"funder_award_id":"62472303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5545798948","display_name":null,"funder_award_id":"62425307","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6274585583","display_name":null,"funder_award_id":"62402334","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,82],"large":[1,7,13],"language":[2,14],"models":[3,9,15],"(MLLMs)":[4],"integrate":[5],"sophisticated":[6],"vision":[8,18,119],"(LVMs)":[10],"to":[11,20,73,93,137,179,206],"empower":[12],"(LLMs)":[16],"with":[17,56,188,216],"ability":[19],"perceive,":[21],"reason,":[22],"and":[23,120,133,158,170,177,183,212],"interact":[24],"in":[25,148],"vision-language":[26],"(V-L)":[27],"tasks,":[28,182],"while":[29],"the":[30,37,49,53,61,88,96,108,115,123,138,142,150,155,159,165,175,201],"modality":[31,54,69],"bridge":[32,55,174],"between":[33,64,168],"two":[34],"specialists":[35],"becomes":[36],"bottleneck":[38],"that":[39,67,86,112,126,146,195],"translates":[40,127],"visual":[41,128,169,202],"signals":[42,129],"into":[43,130],"linguistic":[44,131,171],"representations.":[45],"However,":[46],"most":[47],"of":[48,118],"existing":[50],"methods":[51],"train":[52],"coarse-grained":[57],"image-text":[58],"pairs,":[59],"neglecting":[60],"structural":[62,97],"mapping":[63,167],"V-L":[65,181],"semantics":[66],"facilitates":[68],"translation":[70],"from":[71,91,99,154],"LVMs":[72,92,176],"LLMs.":[74],"To":[75],"mitigate":[76],"this,":[77],"we":[78],"propose":[79],"a":[80],"Constituency-Tree-Induced":[81],"Bridging":[83],"mechanism":[84],"(CTIMB)":[85],"learns":[87],"fine-grained":[89,166],"connection":[90],"LLMs":[94,178,205],"by":[95],"guidance":[98],"multi-modal":[100,109],"constituency":[101],"tree.":[102],"Our":[103],"approach":[104],"consists":[105],"of:":[106],"1)":[107],"constituency-tree":[110,139],"parser":[111,157],"jointly":[113],"exploits":[114],"semantic":[116,151],"structure":[117],"language;":[121],"2)":[122],"lightweight":[124],"connector":[125],"representation":[132],"re-arranges":[134],"them":[135],"according":[136],"structure;":[140],"3)":[141],"dynamic":[143],"construction":[144],"loss":[145],"aids":[147],"aligning":[149],"structures":[152],"derived":[153],"tree":[156],"connector.":[160],"The":[161],"CTIMB":[162],"can":[163],"learn":[164],"semantics,":[172],"seamlessly":[173],"enhance":[180],"is":[184],"more":[185,198,210],"cost-efficient":[186],"compared":[187],"current":[189],"methods.":[190],"Extensive":[191],"experiments":[192],"have":[193],"demonstrated":[194],"our":[196],"method":[197],"accurately":[199],"interprets":[200],"features,":[203],"enabling":[204],"conduct":[207],"downstream":[208],"tasks":[209],"effectively,":[211],"achieve":[213],"superior":[214],"performance":[215],"less":[217],"training":[218],"cost.":[219]},"counts_by_year":[],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-12-03T00:00:00"}
