{"id":"https://openalex.org/W4396758705","doi":"https://doi.org/10.1145/3589334.3645653","title":"Aligning Out-of-Distribution Web Images and Caption Semantics via Evidential Learning","display_name":"Aligning Out-of-Distribution Web Images and Caption Semantics via Evidential Learning","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396758705","doi":"https://doi.org/10.1145/3589334.3645653"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3645653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3645653","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3589334.3645653","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020054896","display_name":"Guohao Sun","orcid":"https://orcid.org/0009-0002-0935-6196"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guohao Sun","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0009-0002-0935-6196","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036001582","display_name":"Yue Bai","orcid":"https://orcid.org/0000-0001-6023-6064"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Bai","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6023-6064","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078772383","display_name":"Xueying Yang","orcid":"https://orcid.org/0009-0001-9777-7902"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueying Yang","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-9777-7902","affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972978","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0001-6572-4315"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["Santa Clara University, Santa CLara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6572-4315","affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa CLara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005819096","display_name":"Yun Fu","orcid":"https://orcid.org/0000-0002-5098-2853"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Fu","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5098-2853","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021486404","display_name":"Zhiqiang Tao","orcid":"https://orcid.org/0000-0002-5639-7540"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Tao","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-5639-7540","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7888,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75487827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2271","last_page":"2281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.991599977016449,"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":0.9891999959945679,"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":0.745310366153717},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6924734115600586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216220617294312},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4526701271533966},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3770790994167328},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10888653993606567},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09791645407676697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745310366153717},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6924734115600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216220617294312},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4526701271533966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3770790994167328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10888653993606567},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09791645407676697},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3645653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3645653","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589334.3645653","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3645653","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2136189984","https://openalex.org/W2185175083","https://openalex.org/W2808787330","https://openalex.org/W2964187781","https://openalex.org/W2997591391","https://openalex.org/W3016842236","https://openalex.org/W3173788106","https://openalex.org/W3206475813","https://openalex.org/W4211116959","https://openalex.org/W4224307896","https://openalex.org/W4224314818","https://openalex.org/W4306317251"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Vision-language":[0],"models,":[1],"pre-trained":[2,193],"on":[3,38,50,89,168],"web-scale":[4],"datasets,":[5],"have":[6],"the":[7,12,79,139,146,187],"potential":[8],"to":[9,65,101,172],"greatly":[10],"enhance":[11],"intelligence":[13],"of":[14,148,155,166,191],"web":[15,106,178],"applications":[16],"(e.g.,":[17,41,158],"search":[18],"engines,":[19],"chatbots,":[20],"and":[21,58,85,108,163,189],"art":[22],"tools).":[23],"Precisely,":[24],"these":[25],"models":[26,195],"align":[27],"disparate":[28],"domains":[29],"into":[30,126],"a":[31,94,153,164],"co-embedding":[32],"space,":[33],"achieving":[34],"impressive":[35],"zero-shot":[36],"performance":[37,67,80,188],"multi-modal":[39],"tasks":[40],"image-text":[42,128,200],"retrieval,":[43],"VQA).":[44],"However,":[45],"existing":[46],"methods":[47],"often":[48],"rely":[49],"well-prepared":[51],"data":[52,175],"that":[53,184],"less":[54],"frequently":[55],"contain":[56],"noise":[57],"variability":[59],"encountered":[60],"in":[61,69,176,199],"real-world":[62,177],"scenarios,":[63],"leading":[64],"severe":[66],"drops":[68],"handling":[70],"out-of-distribution":[71],"(OOD)":[72],"samples.":[73],"This":[74],"work":[75],"first":[76],"comprehensively":[77],"analyzes":[78],"drop":[81],"between":[82,105],"in-distribution":[83],"(ID)":[84],"OOD":[86,113,156,197],"retrieval.":[87],"Based":[88],"empirical":[90],"observations,":[91],"we":[92,150],"introduce":[93],"novel":[95],"approach,":[96],"Evidential":[97],"Language-Image":[98],"Posterior":[99],"(ELIP),":[100],"achieve":[102],"robust":[103],"alignment":[104],"images":[107],"semantic":[109],"knowledge":[110],"across":[111],"various":[112],"cases":[114,157],"by":[115],"leveraging":[116],"evidential":[117],"uncertainties.":[118],"The":[119],"proposed":[120],"ELIP":[121,185],"can":[122],"be":[123],"seamlessly":[124],"integrated":[125],"general":[127],"contrastive":[129],"learning":[130],"frameworks,":[131],"providing":[132],"an":[133],"efficient":[134],"fine-tuning":[135],"approach":[136],"without":[137],"exacerbating":[138],"need":[140],"for":[141],"additional":[142],"data.":[143],"To":[144],"validate":[145],"effectiveness":[147],"ELIP,":[149],"systematically":[151],"design":[152],"series":[154],"image":[159],"distortion,":[160],"spelling":[161],"errors,":[162],"combination":[165],"both)":[167],"two":[169],"benchmark":[170],"datasets":[171],"mimic":[173],"noisy":[174],"applications.":[179],"Our":[180],"experimental":[181],"results":[182],"demonstrate":[183],"improves":[186],"robustness":[190],"mainstream":[192],"vision-language":[194],"facing":[196],"samples":[198],"retrieval":[201],"tasks.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}