{"id":"https://openalex.org/W4402916921","doi":"https://doi.org/10.1109/icip51287.2024.10647426","title":"Distinctive Image Captioning: Leveraging Ground Truth Captions in Clip Guided Reinforcement Learning","display_name":"Distinctive Image Captioning: Leveraging Ground Truth Captions in Clip Guided Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916921","doi":"https://doi.org/10.1109/icip51287.2024.10647426"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647426","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 Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5090399761","display_name":"Antoine Chaffin","orcid":"https://orcid.org/0000-0003-3605-4097"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Chaffin","raw_affiliation_strings":["Univ Rennes,IRISA,Inria,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ Rennes,IRISA,Inria,France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057169414","display_name":"Ewa Kijak","orcid":"https://orcid.org/0000-0003-0232-1097"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ewa Kijak","raw_affiliation_strings":["Univ Rennes,IRISA,Inria,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ Rennes,IRISA,Inria,France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036636249","display_name":"Vincent Claveau","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Claveau","raw_affiliation_strings":["CNRS IRISA,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS IRISA,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69722244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2550","last_page":"2556"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.989300012588501,"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":0.9879000186920166,"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":0.9509098529815674},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7400639653205872},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7359093427658081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7201966643333435},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5169957876205444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4841521382331848},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46252283453941345},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.349974125623703},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3213108777999878}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9509098529815674},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7400639653205872},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7359093427658081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201966643333435},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5169957876205444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4841521382331848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46252283453941345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.349974125623703},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3213108777999878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647426","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2016589492","https://openalex.org/W2119717200","https://openalex.org/W2176263492","https://openalex.org/W2277195237","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2525778437","https://openalex.org/W2578466053","https://openalex.org/W2612675303","https://openalex.org/W2752461516","https://openalex.org/W2886641317","https://openalex.org/W2954841306","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2963456134","https://openalex.org/W2963672599","https://openalex.org/W2964043796","https://openalex.org/W2964268978","https://openalex.org/W3091588028","https://openalex.org/W3166396011","https://openalex.org/W3173220247","https://openalex.org/W3205809313","https://openalex.org/W4281633595","https://openalex.org/W4281686064","https://openalex.org/W4281699561","https://openalex.org/W4288288444","https://openalex.org/W4306820534","https://openalex.org/W4312922092","https://openalex.org/W4319300753","https://openalex.org/W4320013936","https://openalex.org/W4320481739","https://openalex.org/W6678262379","https://openalex.org/W6692846177","https://openalex.org/W6727690538","https://openalex.org/W6732875994","https://openalex.org/W6737479944","https://openalex.org/W6743895910","https://openalex.org/W6765067728","https://openalex.org/W6791353385","https://openalex.org/W6804812009","https://openalex.org/W6838400119","https://openalex.org/W6839015040","https://openalex.org/W6846007759","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","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"],"abstract_inverted_index":{"Training":[0],"image":[1,49,106],"captioning":[2,107],"models":[3,68],"using":[4],"teacher":[5,199],"forcing":[6,200],"results":[7],"in":[8,20,86,98,117,148,192,197],"very":[9,18],"generic":[10],"samples,":[11],"whereas":[12],"more":[13,58],"distinctive":[14,59,242],"captions":[15,93,116,170,243],"can":[16,69,94,122,159,187],"be":[17,70,96,123],"useful":[19,97],"retrieval":[21,39,67],"applications":[22],"or":[23],"to":[24,36,52,57,72,125,136,166,172,178,209,221,240],"produce":[25,241],"alternative":[26],"texts":[27],"describing":[28],"images":[29],"for":[30,80,154],"accessibility.":[31],"Reinforcement":[32],"Learning":[33],"(RL)":[34],"allows":[35],"use":[37,113],"cross-modal":[38,66],"similarity":[40,205],"score":[41],"between":[42],"the":[43,47,54,78,142,167,174,180,193,204,207,210,222,225,233,236],"generated":[44,145],"caption":[45],"and":[46,140],"input":[48],"as":[50,133,161,189,215],"reward":[51,138,177],"guide":[53],"training,":[55],"leading":[56],"captions.":[60,82,227],"Recent":[61],"studies":[62],"show":[63],"that":[64,89,111,131],"pre-trained":[65],"used":[71,124,171],"provide":[73],"this":[74,87,99],"reward,":[75],"completely":[76],"eliminating":[77],"need":[79],"reference":[81],"However,":[83],"we":[84],"argue":[85],"paper":[88],"Ground":[90],"Truth":[91],"(GT)":[92],"still":[95],"RL":[100,194],"framework.":[101],"We":[102],"propose":[103],"a":[104,127,134,149,198],"new":[105],"model":[108],"training":[109,238],"strategy":[110,239],"makes":[112],"of":[114,144,169,182,206,224,235],"GT":[115,208,226],"different":[118],"ways.":[119],"Firstly,":[120],"they":[121,158,186],"train":[126],"simple":[128],"MLP":[129],"discriminator":[130],"serves":[132],"regularization":[135],"prevent":[137],"hacking":[139],"ensures":[141],"fluency":[143],"captions,":[146],"resulting":[147,196],"textual":[150],"GAN":[151],"setup":[152],"extended":[153],"multimodal":[155],"inputs.":[156],"Secondly,":[157],"serve":[160,188],"strong":[162],"baselines":[163],"when":[164],"added":[165],"pool":[168],"compute":[173],"proposed":[175,237],"contrastive":[176],"reduce":[179],"variance":[181],"gradient":[183],"estimate.":[184],"Thirdly,":[185],"additional":[190,217],"trajectories":[191],"strategy,":[195],"loss":[201],"weighted":[202],"by":[203],"image.":[211],"This":[212],"objective":[213],"acts":[214],"an":[216],"learning":[218],"signal":[219],"grounded":[220],"distribution":[223],"Experiments":[228],"on":[229],"MS":[230],"COCO":[231],"demonstrate":[232],"interest":[234],"while":[244],"maintaining":[245],"high":[246],"writing":[247],"quality.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}