{"id":"https://openalex.org/W3196479518","doi":"https://doi.org/10.1145/3460426.3463667","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","display_name":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196479518","doi":"https://doi.org/10.1145/3460426.3463667","mag":"3196479518"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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/A5091066062","display_name":"Jia-Hong Huang","orcid":"https://orcid.org/0000-0001-7943-2591"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jia-Hong Huang","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114858810","display_name":"Ting-Wei Wu","orcid":"https://orcid.org/0000-0002-4927-653X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting-Wei Wu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070684680","display_name":"Marcel Worring","orcid":"https://orcid.org/0000-0003-4097-4136"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcel Worring","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091066062"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":1.8394,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87528392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"652"},"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":0.9969000220298767,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9879999756813049,"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":0.9885178804397583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7936017513275146},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6627659797668457},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6429372429847717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5782697796821594},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46680405735969543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3909878134727478},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36829498410224915},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3463001251220703},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10143053531646729}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9885178804397583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936017513275146},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6627659797668457},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6429372429847717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782697796821594},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46680405735969543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3909878134727478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36829498410224915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3463001251220703},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10143053531646729},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3460426.3463667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/2465a461-a742-484d-bf04-a5f6c92d0b50","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/contextualized-keyword-representations-for-multimodal-retinal-image-captioning(2465a461-a742-484d-bf04-a5f6c92d0b50).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Huang, J-H, Wu, T-W & Worring, M 2021, Contextualized Keyword Representations for Multi-Modal Retinal Image Captioning. in ICMR '21 : proceedings of the 2021 International Conference on Multimedia Retrieval : August 21-24, 2021, Taipei, Taiwan. New York, NY, pp. 645-652, 11th ACM International Conference on Multimedia Retrieval, ICMR 2021, Taipei, Taiwan, Province of China, 16/11/21. https://doi.org/10.1145/3460426.3463667","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/2465a461-a742-484d-bf04-a5f6c92d0b50","is_oa":false,"landing_page_url":"https://hdl.handle.net/11245.1/2465a461-a742-484d-bf04-a5f6c92d0b50","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Huang, J-H, Wu, T-W & Worring, M 2021, Contextualized Keyword Representations for Multi-Modal Retinal Image Captioning. in ICMR '21 : proceedings of the 2021 International Conference on Multimedia Retrieval : August 21-24, 2021, Taipei, Taiwan. New York, NY, pp. 645-652, 11th ACM International Conference on Multimedia Retrieval, ICMR 2021, Taipei, Taiwan, Province of China, 16/11/21. https://doi.org/10.1145/3460426.3463667","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/672161","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/672161","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/2465a461-a742-484d-bf04-a5f6c92d0b50","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/contextualized-keyword-representations-for-multimodal-retinal-image-captioning(2465a461-a742-484d-bf04-a5f6c92d0b50).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICMR '21: proceedings of the 2021 International Conference on Multimedia Retrieval : August 21-24, 2021, Taipei, Taiwan, 645 - 652","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1091878006","https://openalex.org/W1568869800","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969496006","https://openalex.org/W1997259062","https://openalex.org/W2011268029","https://openalex.org/W2033723371","https://openalex.org/W2054928682","https://openalex.org/W2122644916","https://openalex.org/W2125031621","https://openalex.org/W2142192571","https://openalex.org/W2150769593","https://openalex.org/W2152263083","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2332488709","https://openalex.org/W2334175399","https://openalex.org/W2563399268","https://openalex.org/W2600463316","https://openalex.org/W2744143982","https://openalex.org/W2828862258","https://openalex.org/W2882319491","https://openalex.org/W2949376505","https://openalex.org/W2962713692","https://openalex.org/W2963981422","https://openalex.org/W2964018078","https://openalex.org/W2964195337","https://openalex.org/W3009353929","https://openalex.org/W3033386097","https://openalex.org/W3035284526","https://openalex.org/W3103022576","https://openalex.org/W3119639728","https://openalex.org/W3194346615","https://openalex.org/W3198455660"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Medical":[0],"image":[1,19,31,59,63,78,105,116,127,157],"captioning":[2,20,64,128,158],"automatically":[3],"generates":[4],"a":[5,13,23,28,52,121],"medical":[6,15,18,24,30,37,58,62,77,94,104,115,126,156],"description":[7,25,38,95],"to":[8,43,71,143],"describe":[9],"the":[10,48,55,68,90,99,103,111,145,150,164,182],"content":[11],"of":[12,57,67,89,93,113,152,172],"given":[14],"image.":[16],"Traditional":[17],"models":[21],"create":[22],"based":[26,46],"on":[27,47,149],"single":[29],"input":[32,101],"only.":[33],"Hence,":[34],"an":[35,153,170],"abstract":[36],"or":[39],"concept":[40],"is":[41,65,85,130,167],"hard":[42],"be":[44],"generated":[45],"traditional":[49],"approach.":[50,147],"Such":[51],"method":[53],"limits":[54],"effectiveness":[56],"captioning.":[60,117],"Multi-modal":[61],"one":[66,88],"approaches":[69],"utilized":[70],"address":[72],"this":[73,119],"problem.":[74],"In":[75,118],"multi-modal":[76,114,125,155],"captioning,":[79],"textual":[80,100,135],"input,":[81],"e.g.,":[82],"expert-defined":[83],"keywords,":[84],"considered":[86],"as":[87],"main":[91],"drivers":[92],"generation.":[96],"Thus,":[97],"encoding":[98],"and":[102,138,176],"effectively":[106],"are":[107,141],"both":[108],"important":[109],"for":[110],"task":[112],"work,":[120],"new":[122],"end-to-end":[123],"deep":[124],"model":[129,166],"proposed.":[131],"Contextualized":[132],"keyword":[133],"representations,":[134],"feature":[136],"reinforcement,":[137],"masked":[139],"self-attention":[140],"used":[142],"develop":[144],"proposed":[146,165],"Based":[148],"evaluation":[151],"existing":[154],"dataset,":[159],"experimental":[160],"results":[161],"show":[162],"that":[163],"effective":[168],"with":[169,181],"increase":[171],"+53.2%":[173],"in":[174,178],"BLEU-avg":[175],"+18.6%":[177],"CIDEr,":[179],"compared":[180],"state-of-the-art":[183],"method.":[184],"https://github.com/Jhhuangkay/Contextualized-Keyword-Representations-for-Multi-modal-Retinal-Image-Captioning":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}