{"id":"https://openalex.org/W4403792227","doi":"https://doi.org/10.1145/3664647.3681636","title":"AlignCLIP: Align Multi Domains of Texts Input for CLIP models with Object-IoU Loss","display_name":"AlignCLIP: Align Multi Domains of Texts Input for CLIP models with Object-IoU Loss","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792227","doi":"https://doi.org/10.1145/3664647.3681636"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681636?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681636?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100388587","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-9532-5219"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9532-5219","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967246","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0003-3424-4866"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Yan","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3424-4866","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3175-3553","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1092","last_page":"1100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9825999736785889,"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":0.7440413236618042},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6237856149673462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4985818862915039},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4552251100540161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440413236618042},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6237856149673462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4985818862915039},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4552251100540161}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681636?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681636?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403792227.pdf","grobid_xml":"https://content.openalex.org/works/W4403792227.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2886641317","https://openalex.org/W2962933664","https://openalex.org/W2964187781","https://openalex.org/W3090449556","https://openalex.org/W3157014581","https://openalex.org/W3166596953","https://openalex.org/W3176641147","https://openalex.org/W3177224328","https://openalex.org/W3198377975","https://openalex.org/W3208215824","https://openalex.org/W4212774754","https://openalex.org/W4312281439","https://openalex.org/W4312310776","https://openalex.org/W4319300687","https://openalex.org/W4386071472","https://openalex.org/W4390190253","https://openalex.org/W4390874449","https://openalex.org/W4393158799"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Since":[0],"the":[1,4,17,89,97,105,123,136,155,172],"release":[2],"of":[3,91],"CLIP":[5,27,173],"model":[6],"by":[7],"OpenAI,":[8],"it":[9],"has":[10],"received":[11],"widespread":[12],"attention.":[13],"However,":[14,63],"categories":[15],"in":[16],"real":[18],"world":[19],"often":[20],"exhibit":[21],"a":[22,147,180],"long-tail":[23],"distribution,":[24],"and":[25,54,71,114,121,150,175],"existing":[26,177],"models":[28],"struggle":[29],"to":[30,46,57,76,81,95,110,126,135],"effectively":[31],"recognize":[32],"rare,":[33],"tail-end":[34,52],"classes,":[35],"such":[36],"as":[37],"an":[38],"endangered":[39],"African":[40],"bird.":[41],"An":[42],"intuitive":[43],"idea":[44],"is":[45,108],"generate":[47,111,127],"visual":[48,67,112,132],"descriptions":[49,56,113],"for":[50,61],"these":[51,118],"classes":[53],"use":[55,90],"create":[58],"category":[59,128],"prototypes":[60,129],"classification.":[62],"experiments":[64],"reveal":[65],"that":[66,167],"descriptions,":[68],"image":[69],"captions,":[70],"test":[72,115],"prompt":[73],"templates":[74],"belong":[75],"three":[77,119],"distinct":[78],"domains,":[79],"leading":[80],"distribution":[82],"shifts.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"propose":[88],"caption":[92],"object":[93,106,138],"parsing":[94],"identify":[96],"objects":[98],"set":[99],"contained":[100],"within":[101],"captions.":[102],"During":[103],"training,":[104],"sets":[107],"used":[109],"prompts,":[116],"aligning":[117],"domains":[120],"enabling":[122],"text":[124],"encoder":[125],"based":[130],"on":[131],"descriptions.":[133],"Thanks":[134],"acquired":[137],"sets,":[139],"our":[140,168],"approach":[141],"can":[142],"construct":[143],"many-to-many":[144],"relationships":[145],"at":[146],"lower":[148],"cost":[149],"derive":[151],"soft":[152],"labels,":[153],"addressing":[154],"noise":[156],"issues":[157],"associated":[158],"with":[159],"traditional":[160],"one-to-one":[161],"matching.":[162],"Extensive":[163],"experimental":[164],"results":[165],"demonstrate":[166],"method":[169],"significantly":[170],"surpasses":[171],"baseline":[174],"exceeds":[176],"methods,":[178],"achieving":[179],"new":[181],"state-of-the-art":[182],"(SOTA).":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}