{"id":"https://openalex.org/W2963138277","doi":"https://doi.org/10.18653/v1/d18-1435","title":"Entity-aware Image Caption Generation","display_name":"Entity-aware Image Caption Generation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963138277","doi":"https://doi.org/10.18653/v1/d18-1435","mag":"2963138277"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1435","pdf_url":"https://www.aclweb.org/anthology/D18-1435.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 2018 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/D18-1435.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101643267","display_name":"Di Lu","orcid":"https://orcid.org/0000-0002-3054-6325"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Lu","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076767045","display_name":"Spencer Whitehead","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spencer Whitehead","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042819803","display_name":"Lifu Huang","orcid":"https://orcid.org/0000-0002-2743-7718"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifu Huang","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103178893","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-7954-7994"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113668041","display_name":"Shih-Fu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Shih-Fu Chang","raw_affiliation_strings":["Computer Science Department, Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Columbia University","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4013","last_page":"4023"},"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":0.9958999752998352,"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/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8857463598251343},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8317430019378662},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7330597639083862},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6501284837722778},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5994054675102234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5929900407791138},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5534663796424866},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5373861193656921},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48139405250549316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36891889572143555},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3666679263114929},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33796149492263794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11448946595191956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857463598251343},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8317430019378662},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7330597639083862},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6501284837722778},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5994054675102234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929900407791138},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5534663796424866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5373861193656921},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48139405250549316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36891889572143555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3666679263114929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33796149492263794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11448946595191956},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1435","pdf_url":"https://www.aclweb.org/anthology/D18-1435.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1435","pdf_url":"https://www.aclweb.org/anthology/D18-1435.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4818418728","display_name":null,"funder_award_id":"FA8750-18-2-0014","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G523448137","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963138277.pdf","grobid_xml":"https://content.openalex.org/works/W2963138277.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W102708294","https://openalex.org/W1514535095","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1948566616","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1989420837","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2119775030","https://openalex.org/W2123442489","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2149172860","https://openalex.org/W2154652894","https://openalex.org/W2156830856","https://openalex.org/W2157331557","https://openalex.org/W2189472871","https://openalex.org/W2194775991","https://openalex.org/W2250758064","https://openalex.org/W2293174806","https://openalex.org/W2296385829","https://openalex.org/W2325920097","https://openalex.org/W2481240925","https://openalex.org/W2963088515","https://openalex.org/W2963758027","https://openalex.org/W2964308564","https://openalex.org/W3100380967"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Current":[0],"image":[1,33,114],"captioning":[2],"approaches":[3],"generate":[4,31,67],"descriptions":[5,115],"which":[6,28],"lack":[7],"specific":[8,92],"information,":[9],"such":[10],"as":[11,39],"named":[12,93],"entities":[13,94],"that":[14,109],"are":[15],"involved":[16],"in":[17,88],"the":[18,73,89,97],"images.":[19],"In":[20],"this":[21,50],"paper":[22],"we":[23,77],"propose":[24,42],"a":[25,43,55,68,79,101],"new":[26,102],"task":[27],"aims":[29],"to":[30,48,66,86],"informative":[32],"captions,":[34],"given":[35],"images":[36],"and":[37],"hashtags":[38],"input.":[40],"We":[41,52],"simple":[44],"but":[45],"effective":[46],"approach":[47],"tackle":[49],"problem.":[51],"first":[53],"train":[54],"convolutional":[56],"neural":[57],"networks":[58,63],"-long":[59],"short":[60],"term":[61],"memory":[62],"(CNN-LSTM)":[64],"model":[65,111,121],"template":[69,90],"caption":[70],"based":[71,82],"on":[72,100],"input":[74],"image.":[75],"Then":[76],"use":[78],"knowledge":[80],"graph":[81],"collective":[83],"inference":[84],"algorithm":[85],"fill":[87],"with":[91,116,126],"retrieved":[95],"via":[96],"hashtags.":[98],"Experiments":[99],"benchmark":[103],"dataset":[104],"collected":[105],"from":[106],"Flickr":[107],"show":[108],"our":[110],"generates":[112],"news-style":[113],"much":[117],"richer":[118],"information.":[119],"Our":[120],"outperforms":[122],"unimodal":[123],"baselines":[124],"significantly":[125],"various":[127],"evaluation":[128],"metrics.":[129],"1":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}