{"id":"https://openalex.org/W3147635557","doi":"https://doi.org/10.48550/arxiv.2103.04846","title":"Relationship-based Neural Baby Talk","display_name":"Relationship-based Neural Baby Talk","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3147635557","doi":"https://doi.org/10.48550/arxiv.2103.04846","mag":"3147635557"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.04846","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04846","pdf_url":"https://arxiv.org/pdf/2103.04846","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/2103.04846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fu, Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111814593","display_name":"Tingting Xie","orcid":"https://orcid.org/0000-0001-5992-6965","observed_orcids":["https://orcid.org/0000-0001-5992-6965","https://orcid.org/0000-0001-6404-4262"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tingting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031205865","display_name":"Ioannis Patras","orcid":"https://orcid.org/0000-0003-3913-4738","observed_orcids":["https://orcid.org/0000-0003-3913-4738"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patras, Ioannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016652074","display_name":"Sepehr Jalali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jalali, Sepehr","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":0,"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":0.9994999766349792,"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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":0.753000020980835},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.9459999799728394},{"id":"https://openalex.org/keywords/spatial-relationships","display_name":"spatial relations","score":0.7609999775886536},{"id":"https://openalex.org/keywords/semantic-relations","display_name":"semantic relations","score":0.9990000128746033},{"id":"https://openalex.org/keywords/implicit-relationships","display_name":"implicit relationships","score":0.9589999914169312},{"id":"https://openalex.org/keywords/relationship-graph","display_name":"relationship graph","score":0.7630000114440918},{"id":"https://openalex.org/keywords/visual-feature-encoding","display_name":"visual feature encoding","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7901270389556885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639605164527893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5798075199127197},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5281049013137817},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5270901918411255},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4989616870880127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45512861013412476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4425108730792999},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4280739426612854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42269429564476013},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3968237042427063},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2103.04846","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04846","pdf_url":"https://arxiv.org/pdf/2103.04846","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.2103.04846","doi":"https://doi.org/10.48550/arxiv.2103.04846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.04846","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.04846","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04846","pdf_url":"https://arxiv.org/pdf/2103.04846","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":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2479423890","https://openalex.org/W2519887557","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2888680923","https://openalex.org/W2890531016","https://openalex.org/W2964080601","https://openalex.org/W3004349648","https://openalex.org/W3087858011"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W4388145910","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2807634898","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W1692008701"],"abstract_inverted_index":{"Understanding":[0],"interactions":[1,34],"between":[2],"objects":[3,86,98],"in":[4,87,139],"an":[5,8,88],"image":[6,38,89,141],"is":[7],"important":[9],"element":[10],"for":[11],"generating":[12],"captions.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,110],"propose":[18],"a":[19],"relationship-based":[20,42],"neural":[21],"baby":[22],"talk":[23],"(R-NBT)":[24],"model":[25,131],"to":[26,54,60,67],"comprehensively":[27],"investigate":[28],"several":[29],"types":[30,113],"of":[31,96,104,114,119],"pairwise":[32,97],"object":[33],"by":[35],"encoding":[36],"each":[37,120],"via":[39,108],"three":[40,49,81,140],"different":[41,112],"graph":[43],"attention":[44],"networks":[45],"(GATs).":[46],"We":[47,79],"study":[48],"main":[50],"relationships:":[51],"\\textit{spatial":[52],"relationships}":[53,59,66],"explore":[55],"geometric":[56],"interactions,":[57,63],"\\textit{semantic":[58],"extract":[61],"semantic":[62],"and":[64,92],"\\textit{implicit":[65],"capture":[68],"hidden":[69],"information":[70],"that":[71,127],"could":[72],"not":[73],"be":[74],"modelled":[75],"explicitly":[76],"as":[77,90,99],"above.":[78],"construct":[80],"relationship":[82],"graphs":[83],"with":[84],"the":[85,93],"nodes,":[91],"mutual":[94],"relationships":[95,115],"edges.":[100],"By":[101],"exploring":[102],"features":[103,118],"neighbouring":[105],"regions":[106],"individually":[107],"GATs,":[109],"integrate":[111],"into":[116],"visual":[117],"node.":[121],"Experiments":[122],"on":[123,136],"COCO":[124,137],"dataset":[125,138],"show":[126],"our":[128],"proposed":[129],"R-NBT":[130],"outperforms":[132],"state-of-the-art":[133],"models":[134],"trained":[135],"caption":[142],"generation":[143],"tasks.":[144]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}