{"id":"https://openalex.org/W7127147907","doi":"https://doi.org/10.1109/tmm.2026.3660158","title":"CompoVis: Is Cross-Modal Semantic Alignment of CLIP Optimal? A Visual Analysis Attempt","display_name":"CompoVis: Is Cross-Modal Semantic Alignment of CLIP Optimal? A Visual Analysis Attempt","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127147907","doi":"https://doi.org/10.1109/tmm.2026.3660158"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3660158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660158","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/A5124768342","display_name":"Tong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4642-9932","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guodao Sun","orcid":"https://orcid.org/0000-0002-8383-8153"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodao Sun","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8383-8153","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124796841","display_name":"Xueqian Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Zheng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2255-9182","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124830438","display_name":"Qi Jiang","orcid":null},"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":"Qi Jiang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2732-1571","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124816658","display_name":"Wang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Xia","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-4341-3028","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124849657","display_name":"Xu Tan","orcid":null},"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":"Xu Tan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-7378-9245","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124862704","display_name":"Haidong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haidong Gao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-1349-0774","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124844457","display_name":"Haixia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixia Wang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2378-2725","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124849390","display_name":"Ronghua Liang","orcid":null},"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":"Ronghua Liang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2077-9608","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.1094164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3471","last_page":"3486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.932699978351593,"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":0.932699978351593,"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":0.010499999858438969,"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/T12090","display_name":"Language and cultural evolution","score":0.007600000128149986,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6137999892234802},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5830000042915344},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4788999855518341},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46380001306533813},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9039999842643738},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751000046730042},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2711000144481659},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27059999108314514}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3660158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660158","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2861150812","display_name":null,"funder_award_id":"62036009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3381881735","display_name":null,"funder_award_id":"62432014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4281558348","display_name":null,"funder_award_id":"62372411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8416038026","display_name":null,"funder_award_id":"62406287","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8660038754","display_name":null,"funder_award_id":"62422607","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":{"Vision-language":[0],"pre-trained":[1],"models":[2],"(VLMs)":[3],"have":[4],"shown":[5],"impressive":[6],"cross-modal":[7,25],"understanding,":[8],"yet":[9],"their":[10],"\u201ccompositional":[11],"understanding\u201d":[12],"ability":[13],"remains":[14],"under":[15],"investigation.":[16],"We":[17],"introduce":[18],"CompoVis,":[19],"a":[20,113],"framework":[21],"for":[22,119],"visually":[23,40],"probing":[24],"gaps":[26,122],"in":[27,123],"VLMs.":[28,124],"CompoVis":[29,111],"optimizes":[30],"the":[31,91],"grid":[32],"layout":[33],"to":[34,104],"highlight":[35],"alignment":[36,81],"clusters":[37],"and":[38,44,47,60,78,116],"boundaries,":[39],"interprets":[41],"multi-head":[42],"attention":[43],"semantic":[45],"drift,":[46],"enables":[48],"interactive":[49],"fine-tuning":[50,83],"unconstrained":[51],"by":[52],"closed":[53],"datasets":[54],"or":[55],"offline":[56],"models.":[57],"Quantitative":[58],"experiments":[59],"case":[61],"studies":[62],"explore":[63],"key":[64],"insights:":[65],"VLMs":[66],"rely":[67],"on":[68,108],"entity":[69],"shortcuts":[70],"rather":[71],"than":[72],"comprehension-driven;":[73],"stubborn":[74],"global":[75],"modality":[76,121],"isolation":[77],"suboptimal":[79],"fine-grained":[80],"remain;":[82],"with":[84],"negative":[85],"samples":[86],"does":[87],"not":[88],"fundamentally":[89],"alleviate":[90],"gaps.":[92],"Approximately":[93],"89%":[94],"of":[95],"participants":[96],"(<inline-formula":[97],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[99],"notation=\"LaTeX\">$n=27$</tex-math></inline-formula>)":[100],"found":[101],"that,":[102],"compared":[103],"methods":[105],"relying":[106],"solely":[107],"data":[109],"metrics,":[110],"offers":[112],"more":[114],"innovative":[115],"effective":[117],"approach":[118],"investigating":[120]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-02-03T00:00:00"}
