{"id":"https://openalex.org/W4353112693","doi":"https://doi.org/10.48550/arxiv.2303.10766","title":"Multi-modal reward for visual relationships-based image captioning","display_name":"Multi-modal reward for visual relationships-based image captioning","publication_year":2023,"publication_date":"2023-03-19","ids":{"openalex":"https://openalex.org/W4353112693","doi":"https://doi.org/10.48550/arxiv.2303.10766"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2303.10766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10766","pdf_url":"https://arxiv.org/pdf/2303.10766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.10766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Abedi, Ali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abedi, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064679323","display_name":"Hossein Karshenas","orcid":"https://orcid.org/0000-0001-5607-4963","observed_orcids":["https://orcid.org/0000-0001-5607-4963"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karshenas, Hossein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052992615","display_name":"Peyman Adibi","orcid":"https://orcid.org/0000-0001-6411-5235","observed_orcids":["https://orcid.org/0000-0001-6411-5235","https://orcid.org/0000-0003-3247-4828"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adibi, Peyman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/visual-relationships","display_name":"visual relationships","score":0.9789999723434448},{"id":"https://openalex.org/keywords/scene-graph","display_name":"scene graph","score":0.7730000019073486},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9850000143051147},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.6990000009536743},{"id":"https://openalex.org/keywords/object-relations","display_name":"object relations","score":0.3240000009536743}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9781520366668701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062666654586792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7081483006477356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.522984504699707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5087805390357971},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5087500214576721},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5047708749771118},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47406262159347534},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44043588638305664},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43932870030403137},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4368704855442047},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4314126968383789},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4283480644226074},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.425981342792511},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42153507471084595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4153997004032135},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3527592420578003},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0980260968208313},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2303.10766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10766","pdf_url":"https://arxiv.org/pdf/2303.10766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2303.10766","doi":"https://doi.org/10.48550/arxiv.2303.10766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.10766","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2303.10766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10766","pdf_url":"https://arxiv.org/pdf/2303.10766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/8","score":0.4399999976158142,"display_name":"Decent work and economic growth"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3209913752","https://openalex.org/W3036790639","https://openalex.org/W3034733309","https://openalex.org/W3089373619","https://openalex.org/W4318318021","https://openalex.org/W4409521969","https://openalex.org/W4297371741","https://openalex.org/W3170072367","https://openalex.org/W4311808028","https://openalex.org/W3210972247"],"abstract_inverted_index":{"Deep":[0],"neural":[1,105],"networks":[2],"have":[3],"achieved":[4],"promising":[5],"results":[6,161,183],"in":[7,30,52,97,155,176,191],"automatic":[8],"image":[9,35,51,109,203,213],"captioning":[10,36,110,179,204],"due":[11],"to":[12,196,211],"their":[13,85],"effective":[14],"representation":[15,45],"learning":[16,142,194],"and":[17,87,152,209],"context-based":[18],"content":[19],"generation":[20],"capabilities.":[21],"As":[22],"a":[23,43,103,148,156],"prominent":[24],"type":[25],"of":[26,32,46,49,67,81,94,129,143,150,162,172,219],"deep":[27,104,140,192],"features":[28,41],"used":[29],"many":[31],"the":[33,38,50,55,61,65,72,114,125,130,144,166,170,177,182,187,220,223],"recent":[34],"methods,":[37],"well-known":[39],"bottomup":[40],"provide":[42],"detailed":[44,216],"different":[47],"objects":[48,76],"comparison":[53],"with":[54,124],"feature":[56,127],"maps":[57,128],"directly":[58],"extracted":[59,118],"from":[60,119],"raw":[62],"image.":[63,131],"However,":[64],"lack":[66],"high-level":[68],"semantic":[69],"information":[70,117],"about":[71],"relationships":[73,96,116,175],"between":[74],"these":[75],"is":[77,136,226],"an":[78,120],"important":[79],"drawback":[80],"bottom-up":[82],"features,":[83],"despite":[84],"expensive":[86],"resource-demanding":[88],"extraction":[89],"procedure.":[90],"To":[91],"take":[92],"advantage":[93],"visual":[95,115,174],"caption":[98],"generation,":[99],"this":[100],"paper":[101],"proposes":[102],"network":[106,146],"architecture":[107],"for":[108,139],"based":[111],"on":[112,165],"fusing":[113],"image's":[121],"scene":[122],"graph":[123],"spatial":[126],"A":[132,215],"multi-modal":[133,189],"reward":[134,190],"function":[135],"then":[137],"introduced":[138],"reinforcement":[141,193],"proposed":[145,178,188,224],"using":[147,173,207],"combination":[149],"language":[151],"vision":[153],"similarities":[154],"common":[157],"embedding":[158],"space.":[159],"The":[160],"extensive":[163],"experimentation":[164],"MSCOCO":[167],"dataset":[168],"show":[169],"effectiveness":[171],"method.":[180],"Moreover,":[181],"clearly":[184],"indicate":[185],"that":[186],"leads":[195],"better":[197],"model":[198],"optimization,":[199],"outperforming":[200],"several":[201],"state-of-the-art":[202],"algorithms,":[205],"while":[206],"light":[208],"easy":[210],"extract":[212],"features.":[214],"experimental":[217],"study":[218],"components":[221],"constituting":[222],"method":[225],"also":[227],"presented.":[228]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-03-23T00:00:00"}