{"id":"https://openalex.org/W4362563637","doi":"https://doi.org/10.1109/tip.2023.3261743","title":"Cross-Modality Pyramid Alignment for Visual Intention Understanding","display_name":"Cross-Modality Pyramid Alignment for Visual Intention Understanding","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362563637","doi":"https://doi.org/10.1109/tip.2023.3261743","pmid":"https://pubmed.ncbi.nlm.nih.gov/37018096"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3261743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3261743","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3989-7655","affiliations":[{"raw_affiliation_string":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016498084","display_name":"Qinghongya Shi","orcid":"https://orcid.org/0000-0001-9433-2281"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghongya Shi","raw_affiliation_strings":["Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-9433-2281","affiliations":[{"raw_affiliation_string":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089570452","display_name":"Kehua Su","orcid":"https://orcid.org/0000-0002-1384-9762"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehua Su","raw_affiliation_strings":["Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-1384-9762","affiliations":[{"raw_affiliation_string":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Hubei Luojia Laboratory, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.7018,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86376301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2190","last_page":"2201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.7838015556335449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6530436873435974},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6517558693885803},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6031073331832886},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5980098247528076},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5397478342056274},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47722938656806946},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44865697622299194},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4210923910140991},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39559677243232727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08159026503562927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838015556335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6530436873435974},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6517558693885803},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6031073331832886},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5980098247528076},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5397478342056274},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47722938656806946},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44865697622299194},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4210923910140991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39559677243232727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08159026503562927},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3261743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3261743","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37018096","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37018096","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1050597645","display_name":null,"funder_award_id":"2021BAA187","funder_id":"https://openalex.org/F4320336744","funder_display_name":"Science and Technology Program of Hubei Province"},{"id":"https://openalex.org/G170467858","display_name":null,"funder_award_id":"62272354","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8276175874","display_name":null,"funder_award_id":"2022BCA009","funder_id":"https://openalex.org/F4320336744","funder_display_name":"Science and Technology Program of Hubei Province"},{"id":"https://openalex.org/G8800375656","display_name":null,"funder_award_id":"62176188","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"},{"id":"https://openalex.org/F4320336744","display_name":"Science and Technology Program of Hubei Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W46519926","https://openalex.org/W1596905899","https://openalex.org/W1861492603","https://openalex.org/W1899185266","https://openalex.org/W2005308708","https://openalex.org/W2017814585","https://openalex.org/W2070237190","https://openalex.org/W2073775149","https://openalex.org/W2096733369","https://openalex.org/W2108598243","https://openalex.org/W2138621090","https://openalex.org/W2144245116","https://openalex.org/W2152161678","https://openalex.org/W2157439590","https://openalex.org/W2194775991","https://openalex.org/W2200845744","https://openalex.org/W2238867838","https://openalex.org/W2373570000","https://openalex.org/W2463873473","https://openalex.org/W2473931695","https://openalex.org/W2511446577","https://openalex.org/W2589815499","https://openalex.org/W2732026016","https://openalex.org/W2797977484","https://openalex.org/W2803392141","https://openalex.org/W2884528675","https://openalex.org/W2896457183","https://openalex.org/W2899607431","https://openalex.org/W2912990735","https://openalex.org/W2948672349","https://openalex.org/W2956018683","https://openalex.org/W2963037330","https://openalex.org/W2963150697","https://openalex.org/W2963393555","https://openalex.org/W2963446712","https://openalex.org/W2964350391","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2971167298","https://openalex.org/W2979936813","https://openalex.org/W2981058299","https://openalex.org/W2983358816","https://openalex.org/W2997361490","https://openalex.org/W2998356391","https://openalex.org/W3001555892","https://openalex.org/W3010063553","https://openalex.org/W3016201367","https://openalex.org/W3028836324","https://openalex.org/W3034676907","https://openalex.org/W3035524453","https://openalex.org/W3047363187","https://openalex.org/W3093804672","https://openalex.org/W3107848599","https://openalex.org/W3110551393","https://openalex.org/W3133825286","https://openalex.org/W3168433561","https://openalex.org/W3171668871","https://openalex.org/W3172675210","https://openalex.org/W3173685130","https://openalex.org/W3175327592","https://openalex.org/W3176023283","https://openalex.org/W3176143090","https://openalex.org/W3176237992","https://openalex.org/W3177654849","https://openalex.org/W3179267034","https://openalex.org/W3181461461","https://openalex.org/W3189601601","https://openalex.org/W3196691777","https://openalex.org/W3199950635","https://openalex.org/W3209229003","https://openalex.org/W3212145724","https://openalex.org/W3216470601","https://openalex.org/W4200316912","https://openalex.org/W4200343840","https://openalex.org/W4200475325","https://openalex.org/W4214490042","https://openalex.org/W4285141652","https://openalex.org/W4312523492","https://openalex.org/W4312973985","https://openalex.org/W6639927594","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6735377749","https://openalex.org/W6745447533","https://openalex.org/W6745995898","https://openalex.org/W6752959819","https://openalex.org/W6755207826","https://openalex.org/W6756444276","https://openalex.org/W6762718338","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767213583","https://openalex.org/W6773248631","https://openalex.org/W6790904380","https://openalex.org/W6795831278"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Visual":[0],"intention":[1,53,71,80,99,111,150,170],"understanding":[2,50,81,151,171],"is":[3,60,141],"the":[4,8,18,23,48,63,78,107,118,130,146,161],"task":[5,82],"of":[6,51,148,163],"exploring":[7],"potential":[9],"and":[10,69],"underlying":[11],"meaning":[12],"expressed":[13],"in":[14,92,152],"images.":[15],"Simply":[16],"modeling":[17,121],"objects":[19],"or":[20],"backgrounds":[21],"within":[22],"image":[24],"content":[25,68,120],"leads":[26],"to":[27,46,61,97,127,143],"unavoidable":[28],"comprehension":[29],"bias.":[30],"To":[31],"alleviate":[32],"this":[33,35],"problem,":[34,87],"paper":[36],"proposes":[37],"a":[38,84,136,153],"Cross-modality":[39],"Pyramid":[40],"Alignment":[41],"with":[42,54],"Dynamic":[43],"optimization":[44],"(CPAD)":[45],"enhance":[47],"global":[49],"visual":[52,67,74,79,119,149,169],"hierarchical":[55,64,85,98],"modeling.":[56],"The":[57],"core":[58],"idea":[59],"exploit":[62],"relationship":[65],"between":[66,133],"textual":[70,102],"labels.":[72,100],"For":[73,101],"hierarchy,":[75,103],"we":[76,104],"formulate":[77],"as":[83],"classification":[86],"capturing":[88],"multiple":[89],"granular":[90],"features":[91],"different":[93,114,134],"layers,":[94],"which":[95,116],"corresponds":[96],"directly":[105],"extract":[106],"semantic":[108],"representation":[109],"from":[110],"labels":[112],"at":[113],"levels,":[115],"supplements":[117],"without":[122],"extra":[123],"manual":[124],"annotations.":[125],"Moreover,":[126],"further":[128],"narrow":[129],"domain":[131],"gap":[132],"modalities,":[135],"cross-modality":[137],"pyramid":[138],"alignment":[139],"module":[140],"designed":[142],"dynamically":[144],"optimize":[145],"performance":[147],"joint":[154],"learning":[155],"manner.":[156],"Comprehensive":[157],"experiments":[158],"intuitively":[159],"demonstrate":[160],"superiority":[162],"our":[164],"proposed":[165],"method,":[166],"outperforming":[167],"existing":[168],"methods.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}