{"id":"https://openalex.org/W4417073292","doi":"https://doi.org/10.1145/3743093.3770956","title":"OPCap:Object-aware Prompting Captioning","display_name":"OPCap:Object-aware Prompting Captioning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073292","doi":"https://doi.org/10.1145/3743093.3770956"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770956","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018534488","display_name":"Feiyang Huang","orcid":"https://orcid.org/0009-0006-5328-0570"},"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":true,"raw_author_name":"Feiyang Huang","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671670","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-4758-6091"},"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":"Yang Cao","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051336355","display_name":"Jingyue Zhong","orcid":"https://orcid.org/0009-0008-6134-4313"},"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":"Jingyue Zhong","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018534488"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41791844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9771999716758728,"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":0.9771999716758728,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.003700000001117587,"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/T10028","display_name":"Topic Modeling","score":0.0013000000035390258,"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/closed-captioning","display_name":"Closed captioning","score":0.9003000259399414},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.729200005531311},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5752999782562256},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5090000033378601},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4869000017642975},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4138999879360199},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3626999855041504},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3560999929904938},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.35359999537467957}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9003000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609000205993652},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.729200005531311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643000245094299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5909000039100647},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073292.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2904565150","https://openalex.org/W2962735233","https://openalex.org/W2962918138","https://openalex.org/W2963341956","https://openalex.org/W2965697393","https://openalex.org/W2986670728","https://openalex.org/W3042724941","https://openalex.org/W3202965415","https://openalex.org/W4214917601","https://openalex.org/W4285197287","https://openalex.org/W4308946014","https://openalex.org/W4391287688","https://openalex.org/W4401857375"],"related_works":[],"abstract_inverted_index":{"In":[0],"image":[1],"captioning,":[2],"the":[3,56],"phenomenon":[4],"of":[5,66,95],"generating":[6],"descriptions":[7],"with":[8],"missing":[9],"or":[10],"non-existent":[11],"objects":[12],"is":[13],"termed":[14],"hallucination":[15],"(or":[16],"object":[17,45,49],"bias).":[18],"To":[19],"address":[20],"this":[21],"challenge,":[22],"we":[23],"propose":[24],"an":[25,44,60],"Object-aware":[26],"Prompting":[27],"strategy":[28],"(OPCap).":[29],"Unlike":[30],"conventional":[31],"approaches,":[32],"OPCap":[33],"enhances":[34],"semantic":[35,64],"understanding":[36],"through":[37],"a":[38,79],"dual-path":[39],"feature":[40],"fusion":[41,90],"mechanism.":[42],"Specifically,":[43],"detector":[46],"first":[47],"extracts":[48],"tags":[50],"and":[51,83,108,117],"their":[52],"spatial":[53],"positions":[54],"from":[55,73],"image,":[57],"followed":[58],"by":[59,78],"attribute":[61],"predictor":[62],"enriching":[63],"features":[65],"these":[67,74],"objects.":[68],"Structured":[69],"prompt":[70],"sequences":[71],"constructed":[72],"results":[75,105],"are":[76],"processed":[77],"frozen":[80],"language":[81],"model":[82],"further":[84],"encoded":[85],"via":[86],"QFormer.":[87],"This":[88],"information":[89],"ensures":[91],"more":[92],"accurate":[93],"capture":[94],"contextual":[96],"details":[97],"during":[98],"decoding,":[99],"thereby":[100],"improving":[101],"overall":[102],"comprehension.":[103],"Experimental":[104],"on":[106],"COCO":[107],"Nocaps":[109],"datasets":[110],"demonstrate":[111],"OPCap\u2019s":[112],"effectiveness":[113],"in":[114],"suppressing":[115],"hallucinations":[116],"enhancing":[118],"caption":[119],"quality.":[120]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-12-06T00:00:00"}