{"id":"https://openalex.org/W2950315915","doi":"https://doi.org/10.18653/v1/p19-1660","title":"Learning to Relate from Captions and Bounding Boxes","display_name":"Learning to Relate from Captions and Bounding Boxes","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950315915","doi":"https://doi.org/10.18653/v1/p19-1660","mag":"2950315915"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1660","pdf_url":"https://www.aclweb.org/anthology/P19-1660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1660.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sarthak Garg","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sarthak Garg","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joel Ruben Antony Moniz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joel Ruben Antony Moniz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Anshu Aviral","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anshu Aviral","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Priyatham Bollimpalli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyatham Bollimpalli","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1022,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42251873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"6597","last_page":"6603"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.993399977684021,"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/leverage","display_name":"Leverage (statistics)","score":0.7407000064849854},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6859999895095825},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6542999744415283},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.538100004196167},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3968000113964081},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7407000064849854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329999804496765},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6859999895095825},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6542999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6480000019073486},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48100000619888306},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1660","pdf_url":"https://www.aclweb.org/anthology/P19-1660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.00311","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00311","pdf_url":"https://arxiv.org/pdf/1912.00311","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1660","pdf_url":"https://www.aclweb.org/anthology/P19-1660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950315915.pdf","grobid_xml":"https://content.openalex.org/works/W2950315915.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4],"a":[5,19,43,76,102],"novel":[6],"approach":[7,41],"that":[8,120,126],"predicts":[9,124],"the":[10,34,55,60,64,68,90,96,111,115,121,131],"relationships":[11,112],"between":[12],"various":[13],"entities":[14,49],"in":[15,18,50,54,114,130],"an":[16],"image":[17,26],"weakly":[20],"supervised":[21],"manner":[22],"by":[23,100],"relying":[24],"on":[25,95,110],"captions":[27,51,65,84],"and":[28,57,85,106],"object":[29],"bounding":[30],"box":[31],"annotations":[32],"as":[33],"sole":[35],"source":[36],"of":[37,63,92,104,108],"supervision.":[38],"Our":[39],"proposed":[40],"uses":[42],"top-down":[44],"attention":[45],"mechanism":[46],"to":[47,52,66,74],"align":[48,67],"objects":[53],"image,":[56],"then":[58],"leverage":[59],"syntactic":[61],"structure":[62],"relations.":[69],"We":[70,88,117],"use":[71],"these":[72],"alignments":[73],"train":[75],"relation":[77],"classification":[78],"network,":[79],"thereby":[80],"obtaining":[81],"both":[82],"grounded":[83],"dense":[86],"relationships.":[87],"demonstrate":[89],"effectiveness":[91],"our":[93],"model":[94,122],"Visual":[97],"Genome":[98],"dataset":[99],"achieving":[101],"recall@50":[103],"15%":[105],"recall@100":[107],"25%":[109],"present":[113,129],"image.":[116],"also":[118],"show":[119],"successfully":[123],"relations":[125],"are":[127],"not":[128],"corresponding":[132],"captions.":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2019-06-27T00:00:00"}