{"id":"https://openalex.org/W4414360019","doi":"https://doi.org/10.24963/ijcai.2025/169","title":"Semantic-Space-Intervened Diffusive Alignment for Visual Classification","display_name":"Semantic-Space-Intervened Diffusive Alignment for Visual Classification","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360019","doi":"https://doi.org/10.24963/ijcai.2025/169"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/169","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5019051706","display_name":"Zixuan Li","orcid":"https://orcid.org/0009-0007-8037-1344"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041574770","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0003-2672-8406"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085460431","display_name":"Guoqing Chao","orcid":"https://orcid.org/0000-0002-2410-650X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Chao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750540","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-7406-7916"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078383609","display_name":"Yimeng Yang","orcid":"https://orcid.org/0009-0005-5375-8397"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimeng Yang","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoshuo Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuo Yan","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079754643","display_name":"Zhuang Qi","orcid":"https://orcid.org/0000-0003-3433-7413"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080015931","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-9842-4044"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1512","last_page":"1520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9817000031471252,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6991000175476074},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5396000146865845},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4973999857902527},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.49480000138282776},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4481000006198883},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42309999465942383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.39980000257492065},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3993000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803999781608582},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6991000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4973999857902527},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/169","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":[],"abstract_inverted_index":{"Cross-modal":[0],"alignment":[1,113,185],"is":[2,107],"an":[3],"effective":[4],"approach":[5],"to":[6,22,27,45,109,126,205],"improving":[7],"visual":[8,25,133,149],"classification.":[9,100],"Existing":[10],"studies":[11],"typically":[12,36],"enforce":[13],"a":[14,42,70,79,83,103,122],"one-step":[15],"mapping":[16],"that":[17,197],"uses":[18],"deep":[19],"neural":[20],"networks":[21],"project":[23],"the":[24,29,46,51,57,86,95,111,115,128,137,141,145,152,157,164,170,174],"features":[26,93,134,139,168],"mimic":[28],"distribution":[30,52,165],"of":[31,53,59,92,132,140,148,155,166],"textual":[32,167,189],"features.":[33,150,193],"However,":[34],"they":[35],"face":[37],"difficulties":[38],"in":[39,49,85,99],"finding":[40],"such":[41],"projection":[43],"due":[44],"two":[47,116],"modalities":[48],"both":[50,90],"class-wise":[54],"samples":[55],"and":[56,144],"range":[58],"their":[60],"feature":[61,130,181,202],"values.":[62],"To":[63],"address":[64],"this":[65,67],"issue,":[66],"paper":[68],"proposes":[69],"novel":[71],"Semantic-Space-Intervened":[72],"Diffusive":[73],"Alignment":[74],"method,":[75],"termed":[76],"SeDA,":[77,156],"models":[78],"semantic":[80,129,171],"space":[81,131],"as":[82],"bridge":[84],"visual-to-textual":[87],"projection,":[88],"considering":[89],"types":[91],"share":[94],"same":[96],"class-level":[97],"information":[98,190],"More":[101],"importantly,":[102],"bi-stage":[104],"diffusion":[105,142],"framework":[106],"developed":[108],"enable":[110],"progressive":[112],"between":[114],"modalities.":[117],"Specifically,":[118],"SeDA":[119,198],"first":[120],"employs":[121],"Diffusion-Controlled":[123,158],"Semantic":[124,159],"Learner":[125],"model":[127,143],"by":[135],"constraining":[136],"interactive":[138],"category":[146],"centers":[147],"In":[151],"later":[153],"stage":[154],"Translator":[160],"focuses":[161],"on":[162],"learning":[163],"from":[169],"space.":[172],"Meanwhile,":[173],"Progressive":[175],"Feature":[176],"Interaction":[177],"Network":[178],"introduces":[179],"stepwise":[180],"interactions":[182],"at":[183],"each":[184],"step,":[186],"progressively":[187],"integrating":[188],"into":[191],"mapped":[192],"Experimental":[194],"results":[195],"show":[196],"achieves":[199],"stronger":[200],"cross-modal":[201],"alignment,":[203],"leading":[204],"superior":[206],"performance":[207],"over":[208],"existing":[209],"methods":[210],"across":[211],"multiple":[212],"scenarios.":[213]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}