{"id":"https://openalex.org/W2963565375","doi":"https://doi.org/10.18653/v1/d17-1017","title":"Obj2Text: Generating Visually Descriptive Language from Object Layouts","display_name":"Obj2Text: Generating Visually Descriptive Language from Object Layouts","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963565375","doi":"https://doi.org/10.18653/v1/d17-1017","mag":"2963565375"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1017","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1017","pdf_url":"https://www.aclweb.org/anthology/D17-1017.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1017.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032837537","display_name":"Xuwang Yin","orcid":"https://orcid.org/0000-0001-7572-9144"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuwang Yin","raw_affiliation_strings":["Department of Computer Science, University of Virginia, Charlottesville, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia, Charlottesville, VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027328044","display_name":"Vicente Ord\u00f3\u00f1ez","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vicente Ordonez","raw_affiliation_strings":["Department of Computer Science, University of Virginia, Charlottesville, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia, Charlottesville, VA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027328044"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"187"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.8073391914367676},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.7106208205223083},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6844520568847656},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6558164358139038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6365058422088623},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6066434383392334},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.574249267578125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5020709037780762},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48096147179603577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47848600149154663},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4778116047382355},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4675995707511902},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.439965158700943},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32910507917404175},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24537575244903564},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2368628978729248},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.18433436751365662},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08740639686584473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073391914367676},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.7106208205223083},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6844520568847656},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6558164358139038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6365058422088623},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6066434383392334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.574249267578125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5020709037780762},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48096147179603577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47848600149154663},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4778116047382355},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4675995707511902},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.439965158700943},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32910507917404175},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24537575244903564},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2368628978729248},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.18433436751365662},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08740639686584473},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1017","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1017","pdf_url":"https://www.aclweb.org/anthology/D17-1017.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1017","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1017","pdf_url":"https://www.aclweb.org/anthology/D17-1017.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963565375.pdf","grobid_xml":"https://content.openalex.org/works/W2963565375.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W825973156","https://openalex.org/W1514535095","https://openalex.org/W1681454004","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1902237438","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1948566616","https://openalex.org/W1956340063","https://openalex.org/W1982185844","https://openalex.org/W1996418862","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2117539524","https://openalex.org/W2125436662","https://openalex.org/W2131179926","https://openalex.org/W2133564696","https://openalex.org/W2143449221","https://openalex.org/W2162861726","https://openalex.org/W2163605009","https://openalex.org/W2164079290","https://openalex.org/W2196779496","https://openalex.org/W2251848082","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2462848072","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2516621648","https://openalex.org/W2552161745","https://openalex.org/W2570343428","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2962891517","https://openalex.org/W2963472289","https://openalex.org/W2963735856","https://openalex.org/W2964308564","https://openalex.org/W3098232790","https://openalex.org/W4290937004","https://openalex.org/W4300521955","https://openalex.org/W4394663744"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W2975200075","https://openalex.org/W2007544051","https://openalex.org/W4224006678","https://openalex.org/W4323830248","https://openalex.org/W1837097281","https://openalex.org/W1966410754","https://openalex.org/W2363840281","https://openalex.org/W2325242284","https://openalex.org/W2789220062"],"abstract_inverted_index":{"Generating":[0],"captions":[1],"for":[2,21],"images":[3],"is":[4,32],"a":[5,33,43,48,82,105,125],"task":[6,106],"that":[7,46,74,93,120],"has":[8],"recently":[9],"received":[10],"considerable":[11],"attention.":[12],"In":[13],"this":[14,65],"work":[15],"we":[16],"focus":[17],"on":[18],"caption":[19],"generation":[20],"abstract":[22],"scenes,":[23],"or":[24],"object":[25,79,113,127],"layouts":[26,80],"where":[27],"the":[28,141,145],"only":[29,112],"information":[30],"provided":[31],"set":[34,49],"of":[35,50,107,144],"objects":[36,51],"and":[37,52,63,90,97],"their":[38,53],"locations.":[39],"We":[40,72,100,117],"propose":[41],"OBJ2TEXT,":[42],"sequence-tosequence":[44],"model":[45,133],"encodes":[47],"locations":[54],"as":[55,81,115],"an":[56,60,68,130],"input":[57],"sequence":[58],"using":[59,67,111],"LSTM":[61,69],"network,":[62],"decodes":[64],"representation":[66],"language":[70],"model.":[71],"show":[73,119],"our":[75,102,121],"model,":[76,122],"despite":[77],"encoding":[78],"sequence,":[83],"can":[84],"represent":[85],"spatial":[86],"relationships":[87],"between":[88],"objects,":[89],"generate":[91],"descriptions":[92],"are":[94],"globally":[95],"coherent":[96],"semantically":[98],"relevant.":[99],"test":[101,142],"approach":[103],"in":[104,140],"object-layout":[108],"captioning":[109,132],"by":[110],"annotations":[114],"inputs.":[116],"additionally":[118],"combined":[123],"with":[124],"state-of-the-art":[126],"detector,":[128],"improves":[129],"image":[131],"from":[134],"0.863":[135],"to":[136],"0.950":[137],"(CIDEr":[138],"score)":[139],"benchmark":[143],"standard":[146],"MS-COCO":[147],"Captioning":[148],"task.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":8}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}