{"id":"https://openalex.org/W2965597639","doi":"https://doi.org/10.1145/3343031.3350943","title":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","display_name":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2965597639","doi":"https://doi.org/10.1145/3343031.3350943","mag":"2965597639"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.02127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Longteng Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinhui Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiangwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangwei Li","raw_affiliation_strings":["Huawei Devices, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Devices, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Luo","raw_affiliation_strings":["Huawei Devices, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Devices, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hanqing Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Lu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"765","last_page":"773"},"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":0.9909999966621399,"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":0.9854999780654907,"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/closed-captioning","display_name":"Closed captioning","score":0.6470999717712402},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5491999983787537},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5461000204086304},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4959999918937683},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39590001106262207},{"id":"https://openalex.org/keywords/semantic-property","display_name":"Semantic property","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6523000001907349},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.3700999915599823},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3343031.3350943","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.02127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.02127","pdf_url":"https://arxiv.org/pdf/1908.02127","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":"pmh:oai:arXiv.org:1908.02127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.02127","pdf_url":"https://arxiv.org/pdf/1908.02127","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G223243399","display_name":null,"funder_award_id":"61872366,61872364","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2077069816","https://openalex.org/W2277195237","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2886970679","https://openalex.org/W2890531016","https://openalex.org/W2955956881","https://openalex.org/W2963101956","https://openalex.org/W2963448089","https://openalex.org/W2963536419","https://openalex.org/W2964094751","https://openalex.org/W2964284374"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,185],"attempts":[2],"to":[3,15,38,83,194],"generate":[4],"a":[5,72,76,84,94,122],"sentence":[6],"composed":[7],"of":[8,132,151],"several":[9],"linguistic":[10,60],"words,":[11],"which":[12,149],"are":[13,110,178,190],"used":[14],"describe":[16],"objects,":[17],"attributes,":[18],"and":[19,46,54,62,75,137,164,187],"interactions":[20,43],"in":[21,29,44],"an":[22,89,91],"image,":[23],"denoted":[24],"as":[25,128],"visual":[26,63,85,134,152,170],"semantic":[27,64,73,86,95,103,135,153,171],"units":[28,65,136,145,172],"this":[30,34,174],"paper.":[31],"Based":[32],"on":[33,49,180],"view,":[35],"we":[36,70],"propose":[37],"explicitly":[39],"model":[40],"the":[41,57,102,113,130,133,140,159,167,181],"object":[42],"semantics":[45],"geometry":[47,77],"based":[48],"Graph":[50],"Convolutional":[51],"Networks":[52],"(GCNs),":[53],"fully":[55],"exploit":[56],"alignment":[58],"between":[59,98],"words":[61],"for":[66,107],"image":[67,184],"captioning.":[68],"Particularly,":[69],"construct":[71],"graph":[74],"graph,":[78],"where":[79],"each":[80,108,119],"node":[81],"corresponds":[82],"unit,":[87],"i.e.,":[88],"object,":[90],"attribute,":[92,156],"or":[93,157],"(geometrical)":[96,104],"interaction":[97],"two":[99],"objects.":[100],"Accordingly,":[101],"context-aware":[105],"embeddings":[106,131],"unit":[109,154],"obtained":[111],"through":[112],"corresponding":[114],"GCN":[115],"learning":[116],"processers.":[117],"At":[118],"time":[120],"step,":[121],"context":[123],"gated":[124],"attention":[125],"module":[126],"takes":[127],"inputs":[129],"hierarchically":[138],"align":[139],"current":[141,160],"word":[142,161],"with":[143],"these":[144],"by":[146],"first":[147],"deciding":[148],"type":[150],"(object,":[155],"interaction)":[158],"is":[162],"about,":[163],"then":[165],"finding":[166],"most":[168],"correlated":[169],"under":[173],"type.":[175],"Extensive":[176],"experiments":[177],"conducted":[179],"challenging":[182],"MS-COCO":[183],"dataset,":[186],"superior":[188],"results":[189],"reported":[191],"when":[192],"comparing":[193],"state-of-the-art":[195],"approaches.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-08-13T00:00:00"}