{"id":"https://openalex.org/W4406611893","doi":"https://doi.org/10.1109/smc54092.2024.10831699","title":"ROP: Exploring Image Captioning with Retrieval-Augmented and Object Detection of Prompt","display_name":"ROP: Exploring Image Captioning with Retrieval-Augmented and Object Detection of Prompt","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611893","doi":"https://doi.org/10.1109/smc54092.2024.10831699"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100691593","display_name":"Meng Zhang","orcid":"https://orcid.org/0000-0003-1465-9714"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Zhang","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083785658","display_name":"Kai Yang","orcid":"https://orcid.org/0000-0001-5571-6645"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yang","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091307985","display_name":"Shouqiang Liu","orcid":"https://orcid.org/0000-0002-2795-0685"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouqiang Liu","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University, Nanhai,Faculty of Engineering,Foshan,Guangdong,China,528225","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.24073127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9904999732971191,"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":0.9811000227928162,"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":0.9656510353088379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922909259796143},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6261864304542542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6198205351829529},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.595234751701355},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5547646880149841},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.539844274520874},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.46163487434387207},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4194057285785675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19352471828460693}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9656510353088379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922909259796143},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6261864304542542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198205351829529},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.595234751701355},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5547646880149841},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.539844274520874},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.46163487434387207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4194057285785675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19352471828460693}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2904565150","https://openalex.org/W2997591391","https://openalex.org/W2998702515","https://openalex.org/W3091588028","https://openalex.org/W4213189167","https://openalex.org/W4292828275","https://openalex.org/W4303444943","https://openalex.org/W4372337842","https://openalex.org/W4386076004","https://openalex.org/W4389520529","https://openalex.org/W6639432524","https://openalex.org/W6791353385","https://openalex.org/W6800139874","https://openalex.org/W6803567076","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6853507575","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"models":[2],"aim":[3],"to":[4,55,65,68,117,150,159],"bridge":[5],"the":[6,19,43,60,66,85,125,132,135,138,141,145,151,161,165,169,173,184],"modalities":[7],"of":[8,21,48,87,127,134,164,176],"vision":[9],"and":[10,40,73,82,115,192],"language":[11,15,38],"by":[12,33,41,179],"generating":[13,28],"natural":[14],"descriptions":[16],"that":[17,112],"match":[18],"content":[20],"an":[22],"input":[23,152],"image.":[24,185],"Existing":[25],"methods":[26],"for":[27],"image":[29,88,166],"captions":[30],"do":[31],"so":[32],"integrating":[34],"visual":[35,71],"encoders":[36],"with":[37],"models,":[39],"training":[42],"model":[44,142],"using":[45],"large":[46],"volumes":[47],"image-text":[49],"pairs.":[50],"However,":[51],"this":[52,103,119,155],"approach":[53,122],"leads":[54],"a":[56,99,107],"significant":[57],"increase":[58],"in":[59,80,194],"model's":[61,174],"parameter":[62],"size":[63],"due":[64],"need":[67],"store":[69],"extensive":[70],"concepts":[72],"detailed":[74],"textual":[75],"descriptions.":[76,136],"With":[77],"substantial":[78],"investments":[79],"datasets":[81],"computational":[83],"resources,":[84],"quality":[86],"caption":[89],"generation":[90],"has":[91,188],"notably":[92],"improved,":[93],"though":[94],"these":[95],"advancements":[96],"come":[97],"at":[98],"high":[100],"cost.":[101],"In":[102],"paper,":[104],"we":[105],"introduce":[106],"novel":[108],"method,":[109],"termed":[110],"ROP,":[111],"combines":[113],"retrieval":[114,139],"detection":[116,170],"address":[118],"challenge.":[120],"This":[121],"significantly":[123],"reduces":[124],"number":[126],"trainable":[128],"parameters":[129],"while":[130],"preserving":[131],"accuracy":[133],"Through":[137],"module,":[140],"can":[143],"find":[144],"k":[146],"most":[147],"similar":[148],"sentences":[149],"image,":[153],"utilizing":[154],"rich":[156],"contextual":[157],"information":[158],"enhance":[160],"overall":[162],"understanding":[163],"content.":[167],"Simultaneously,":[168],"module":[171],"enhances":[172],"interpretation":[175],"fine":[177],"details":[178],"identifying":[180],"prominent":[181],"regions":[182],"within":[183],"Our":[186],"method":[187],"proven":[189],"its":[190],"effectiveness":[191],"feasibility":[193],"experiments.":[195]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}