{"id":"https://openalex.org/W7130711519","doi":"https://doi.org/10.1109/tmm.2026.3660118","title":"Adaptively Clustering Neighbor Elements for Image-Text Generation","display_name":"Adaptively Clustering Neighbor Elements for Image-Text Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7130711519","doi":"https://doi.org/10.1109/tmm.2026.3660118"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3660118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660118","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5101444415","display_name":"Zihua Wang","orcid":"https://orcid.org/0009-0009-5127-0143"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihua Wang","raw_affiliation_strings":["School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-5871-6973","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088751229","display_name":"Xia Yang","orcid":"https://orcid.org/0000-0002-3971-038X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126503040","display_name":"Haiyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["College of Computing &amp; Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"College of Computing &amp; Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126491116","display_name":"Ming Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488344","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021485957","display_name":"Youqi Zhang","orcid":"https://orcid.org/0000-0003-4555-5061"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0140-7366","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.16819933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"4475","last_page":"4484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.974399983882904,"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":0.974399983882904,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.011099999770522118,"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/T10028","display_name":"Topic Modeling","score":0.0019000000320374966,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6811000108718872},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.611299991607666},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5651999711990356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.52920001745224},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4934999942779541},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4596000015735626},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4514999985694885},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42410001158714294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619999885559082},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6811000108718872},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5651999711990356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3660118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660118","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/211910","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/211910","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6946537494659424,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1840098831","display_name":null,"funder_award_id":"62576091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3290388347","display_name":null,"funder_award_id":"62576089","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,40,51,67,104,121,136],"novel":[3,41],"Transformer-based":[4],"image-to-text":[5,166],"generation":[6],"model":[7],"termed":[8],"as":[9],"<bold":[10],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[11],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ACF</b>":[12],"that":[13,44,70],"adaptively":[14],"clusters":[15,95,110],"vision":[16,144,159],"patches":[17],"into":[18,24,103,113],"object":[19],"regions":[20],"and":[21,78,146,155,170,187,190],"language":[22,147,161],"words":[23],"phrases":[25],"to":[26,90,141,160],"implicitly":[27],"learn":[28],"object-phrase":[29,151],"alignments":[30,152],"for":[31],"better":[32],"visual-text":[33],"coherence.":[34],"To":[35],"achieve":[36],"this,":[37],"we":[38],"design":[39],"self-attention":[42,46,88],"layer":[43],"applies":[45],"over":[47],"the":[48,57,74,93,97,128,132,143,149,178],"elements":[49],"in":[50,96,163],"local":[52],"cluster":[53],"window":[54,61],"instead":[55],"of":[56,131,180],"whole":[58],"sequence.":[59,134],"The":[60,174],"size":[62],"is":[63,71,82,124],"softly":[64],"decided":[65],"by":[66,73,138],"clustering":[68,119],"matrix":[69],"calculated":[72],"current":[75],"input":[76,133],"data":[77],"thus":[79],"this":[80,117],"process":[81],"adaptive.":[83],"By":[84],"stacking":[85],"these":[86],"revised":[87],"layers":[89,99],"construct":[91],"ACF,":[92,181],"small":[94,111],"lower":[98],"can":[100],"be":[101],"grouped":[102],"bigger":[105,114],"cluster,":[106],"e.g.,":[107],"vision/language.":[108],"ACF":[109,140],"objects/phrases":[112],"ones.":[115],"In":[116],"gradual":[118],"process,":[120],"parsing":[122],"tree":[123],"generated":[125],"which":[126,182],"embeds":[127],"hierarchical":[129,150],"knowledge":[130],"As":[135],"result,":[137],"using":[139],"build":[142],"encoder":[145],"decoder,":[148],"are":[153],"embedded":[154],"then":[156],"transferred":[157],"from":[158],"domains":[162],"two":[164],"popular":[165],"tasks:":[167],"Image":[168],"captioning":[169,186],"Visual":[171],"Question":[172],"Answering.":[173],"experiment":[175],"results":[176],"demonstrate":[177],"effectiveness":[179],"outperforms":[183],"most":[184],"SOTA":[185],"VQA":[188],"models":[189],"achieves":[191],"comparable":[192],"scores":[193],"compared":[194],"with":[195],"some":[196],"large-scale":[197],"pre-trained":[198],"models.":[199]},"counts_by_year":[],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2026-02-21T00:00:00"}