{"id":"https://openalex.org/W4412396367","doi":"https://doi.org/10.1145/3726302.3729923","title":"Class Activation Values: Lucid and Faithful Visual Interpretations for CLIP-based Text-Image Retrievals","display_name":"Class Activation Values: Lucid and Faithful Visual Interpretations for CLIP-based Text-Image Retrievals","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412396367","doi":"https://doi.org/10.1145/3726302.3729923"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3726302.3729923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5111332941","display_name":"Pengxu Chen","orcid":"https://orcid.org/0009-0000-0637-8184"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxu Chen","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0009-0000-0637-8184","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034601329","display_name":"Huazhong Liu","orcid":"https://orcid.org/0000-0001-7813-5894"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Liu","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0001-7813-5894","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086641506","display_name":"Jihong Ding","orcid":"https://orcid.org/0000-0002-2939-6171"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Ding","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0002-2939-6171","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinghao Huang","orcid":"https://orcid.org/0009-0002-6088-8585"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghao Huang","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0009-0002-6088-8585","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762044","display_name":"Shaojun Zou","orcid":"https://orcid.org/0009-0007-3694-9532"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Zou","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0009-0007-3694-9532","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049154222","display_name":"Laurence T. Yang","orcid":"https://orcid.org/0000-0002-7986-4244"},"institutions":[{"id":"https://openalex.org/I197191942","display_name":"St. Francis Xavier University","ror":"https://ror.org/01wcaxs37","country_code":"CA","type":"education","lineage":["https://openalex.org/I197191942"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laurence Tianruo Yang","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China and St. Francis Xavier University, Antigonish, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7986-4244","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China and St. Francis Xavier University, Antigonish, Canada","institution_ids":["https://openalex.org/I197191942"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.14356322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"844","last_page":"853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9904000163078308,"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":0.9904000163078308,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9847999811172485,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.679870069026947},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6593871712684631},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5429356694221497},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4599880278110504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667910695075989},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35212913155555725},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34630444645881653},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33325526118278503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679870069026947},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6593871712684631},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5429356694221497},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4599880278110504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667910695075989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35212913155555725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34630444645881653},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33325526118278503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3726302.3729923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2606462007","https://openalex.org/W2612690371","https://openalex.org/W2616247523","https://openalex.org/W2765793020","https://openalex.org/W2776207810","https://openalex.org/W2946794439","https://openalex.org/W2964612343","https://openalex.org/W2990138404","https://openalex.org/W3015214599","https://openalex.org/W3022265721","https://openalex.org/W3094502228","https://openalex.org/W3101609372","https://openalex.org/W3112516115","https://openalex.org/W3127698310","https://openalex.org/W3135367836","https://openalex.org/W3159344844","https://openalex.org/W3175267326","https://openalex.org/W3176482836","https://openalex.org/W4248927948","https://openalex.org/W4385768130","https://openalex.org/W4387560545","https://openalex.org/W4387947074","https://openalex.org/W4390438191","https://openalex.org/W4394712470","https://openalex.org/W4396787111","https://openalex.org/W4400526206","https://openalex.org/W4400528838","https://openalex.org/W4400529824","https://openalex.org/W4402671694","https://openalex.org/W4402727630","https://openalex.org/W4403792134","https://openalex.org/W6730342312","https://openalex.org/W6739901393","https://openalex.org/W6862497184"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W2121496884","https://openalex.org/W2387910809","https://openalex.org/W2294221496"],"abstract_inverted_index":{"Transformer-based":[0],"text-image":[1,17,72],"matching":[2],"model,":[3],"known":[4],"as":[5],"CLIP,":[6],"has":[7],"garnered":[8],"significant":[9],"attention":[10],"owing":[11],"to":[12,63,89,103,130],"its":[13,131],"exceptional":[14],"performance":[15],"in":[16,160],"retrieval":[18],"tasks":[19],"and":[20,39,45,66,80,85,110,126,137,145,149,163,168],"downstream":[21],"applications.":[22],"However,":[23],"the":[24,43,94,114,143,150],"interpret-ability":[25],"of":[26,82,122],"CLIP":[27],"remains":[28],"underexplored.":[29],"Existing":[30],"interpretation":[31,56,158],"methods":[32,159],"for":[33,70,93],"Transformers":[34],"often":[35],"struggle":[36],"with":[37],"incomplete":[38],"unreliable":[40],"attributions":[41],"within":[42,113],"image":[44,95,167],"text":[46,115,169],"modalities,":[47],"respectively.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,75,98],"propose":[53],"a":[54],"fine-grained":[55,105],"method,":[57],"termed":[58],"Class":[59],"Activation":[60],"Values":[61],"(CAV),":[62],"provide":[64],"lucid":[65],"faithful":[67],"visual":[68],"explanations":[69,92,128],"CLIP-based":[71],"retrievals.":[73],"Specifically,":[74],"systematically":[76],"perform":[77],"multi-scale":[78],"accumulation":[79],"fusion":[81],"class-specific":[83],"gradients":[84],"activation":[86],"value":[87,108],"features":[88,109],"generate":[90],"high-definition":[91],"encoder.":[96,116],"Furthermore,":[97],"present":[99],"element-wise":[100],"gradient-based":[101],"weights":[102],"attribute":[104],"relevance":[106],"between":[107],"output":[111],"similarity":[112],"The":[117],"proposed":[118],"CAV":[119,155],"is":[120],"capable":[121],"simultaneously":[123],"rendering":[124],"detailed":[125],"credible":[127],"due":[129],"precise":[132],"feature":[133],"attribution.":[134],"Extensive":[135],"qualitative":[136],"quantitative":[138],"experiments":[139],"are":[140],"conducted":[141],"on":[142],"ImageNet-1k":[144],"MS":[146],"COCO":[147],"datasets,":[148],"experimental":[151],"results":[152],"demonstrate":[153],"that":[154],"outperforms":[156],"state-of-the-art":[157],"both":[161],"faithfulness":[162],"localization":[164],"assessments":[165],"across":[166],"modalities.":[170]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}