{"id":"https://openalex.org/W4388185726","doi":"https://doi.org/10.1145/3581783.3612326","title":"CONICA: A Contrastive Image Captioning Framework with Robust Similarity Learning","display_name":"CONICA: A Contrastive Image Captioning Framework with Robust Similarity Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388185726","doi":"https://doi.org/10.1145/3581783.3612326"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101816456","display_name":"Lin Deng","orcid":"https://orcid.org/0000-0003-0177-7252"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Deng","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035611029","display_name":"Yuzhong Zhong","orcid":"https://orcid.org/0000-0001-8046-1904"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhong Zhong","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074057419","display_name":"Maoning Wang","orcid":"https://orcid.org/0000-0001-7076-9112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maoning Wang","raw_affiliation_strings":["College of Electrical Engineering, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Chengdu, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326967","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-5491-1745"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101816456"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":0.3685,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60905006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5109","last_page":"5119"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9937000274658203,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9902999997138977,"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/closed-captioning","display_name":"Closed captioning","score":0.9816817045211792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850317358970642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792537331581116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5322845578193665},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47857001423835754},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4509451389312744},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4441967308521271},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42685580253601074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3321858048439026}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9816817045211792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850317358970642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792537331581116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5322845578193665},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47857001423835754},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4509451389312744},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4441967308521271},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42685580253601074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3321858048439026},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1529296559","display_name":null,"funder_award_id":"No.2023SCU12003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G239177072","display_name":null,"funder_award_id":"No.62203314","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108862644","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2949376505","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3103022576","https://openalex.org/W3153332739","https://openalex.org/W3167939936","https://openalex.org/W3196122027","https://openalex.org/W3202965415","https://openalex.org/W4221147537","https://openalex.org/W4304092583","https://openalex.org/W4386076674"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W4388002133","https://openalex.org/W2086811659"],"abstract_inverted_index":{"Contrastive":[0],"Language":[1],"Image":[2,52],"Pre-training":[3],"(CLIP)":[4],"has":[5],"recently":[6],"made":[7],"significant":[8],"advancements":[9],"in":[10],"image":[11,63,77,101],"captioning":[12,34,64,78,112,130],"by":[13],"providing":[14],"effective":[15],"multi-modal":[16],"representation":[17],"learning":[18,59,72],"capabilities.":[19],"However,":[20],"previous":[21],"studies":[22],"primarily":[23],"rely":[24],"on":[25,137],"the":[26,33,37,75,97,106,111,138],"language-aligned":[27],"visual":[28],"semantics":[29],"as":[30],"input":[31],"for":[32,117],"model,":[35],"leaving":[36],"learned":[38,107],"robust":[39],"vision-language":[40],"relevance":[41],"under-exploited.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,69,85,104],"propose":[47],"CONICA,":[48],"a":[49],"unified":[50],"CONtrastive":[51],"CAptioning":[53],"framework":[54],"that":[55,94,123],"investigates":[56],"how":[57],"contrastive":[58,71,88,108],"can":[60],"further":[61],"enhance":[62],"from":[65],"three":[66],"aspects.":[67],"Firstly,":[68],"introduce":[70],"objectives":[73],"into":[74,110],"typical":[76],"training":[79],"pipeline":[80],"with":[81,96],"minimal":[82],"overhead.":[83],"Secondly,":[84],"construct":[86],"fine-grained":[87],"samples":[89],"to":[90,115],"obtain":[91],"image-text":[92],"similarities":[93],"correlate":[95],"evaluation":[98],"metric":[99],"of":[100],"captioning.":[102],"Finally,":[103],"incorporate":[105],"knowledge":[109],"decoding":[113],"strategy":[114],"search":[116],"better":[118],"captions.":[119],"Experimental":[120],"results":[121,136],"demonstrate":[122],"CONICA":[124],"significantly":[125],"improves":[126],"performance":[127],"over":[128],"standard":[129],"baselines":[131],"and":[132,140],"achieves":[133],"new":[134],"state-of-the-art":[135],"MSCOCO":[139],"Flikr30K.":[141],"Source":[142],"code":[143],"is":[144],"available":[145],"at":[146],"https://github.com/DenglinGo/CONICA.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}