{"id":"https://openalex.org/W2905288264","doi":"https://doi.org/10.1609/aaai.v33i01.33018885","title":"Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding","display_name":"Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905288264","doi":"https://doi.org/10.1609/aaai.v33i01.33018885","mag":"2905288264"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4916/4789","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4916/4789","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090707276","display_name":"Lingyun Song","orcid":"https://orcid.org/0000-0002-7892-2617"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyun Song","raw_affiliation_strings":["Xi'an JiaoTong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an JiaoTong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Xi'an Jiaotong Univerisity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong Univerisity","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074506574","display_name":"Buyue Qian","orcid":"https://orcid.org/0000-0003-4780-5677"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Buyue Qian","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042050339","display_name":"Yihe Chen","orcid":"https://orcid.org/0000-0002-2336-6182"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yihe Chen","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.732,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.78776931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":"01","first_page":"8885","last_page":"8892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9835000038146973,"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":0.9491000175476074,"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":0.9495640993118286},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.8244753479957581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851154208183289},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7164523005485535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.647727906703949},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6069446802139282},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5253000855445862},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4641526937484741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40980079770088196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40561771392822266}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9495640993118286},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.8244753479957581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851154208183289},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7164523005485535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647727906703949},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6069446802139282},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5253000855445862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4641526937484741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40980079770088196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40561771392822266},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4916/4789","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4916","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4916/4789","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3340281837","display_name":"\u788e\u7247\u5316\u77e5\u8bc6\u805a\u5408\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61532015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4593145466","display_name":"\u591a\u6e90RDF\u6570\u636e\u51b2\u7a81\u6d88\u89e3\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61672418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4596521664","display_name":null,"funder_award_id":"2018YFB1004500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5897914623","display_name":null,"funder_award_id":"61721002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6122029691","display_name":"\u9762\u5411\u5f00\u653e\u77e5\u8bc6\u6e90\u7684\u77e5\u8bc6\u788e\u7247\u5206\u9762\u805a\u5408\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61672419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6387986177","display_name":null,"funder_award_id":"61721002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6649825942","display_name":null,"funder_award_id":"No. 2017A010101029","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"},{"id":"https://openalex.org/G6746171846","display_name":"\u5927\u89c4\u6a21\u5728\u7ebf\u534f\u540c\u5b66\u4e60\u7684\u673a\u7406\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61532004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8024359634","display_name":null,"funder_award_id":"61532004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8257415233","display_name":null,"funder_award_id":"201706280198","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8553518352","display_name":null,"funder_award_id":"61532015","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905288264.pdf","grobid_xml":"https://content.openalex.org/works/W2905288264.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1514535095","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2112912048","https://openalex.org/W2123301721","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2153579005","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2179488730","https://openalex.org/W2185175083","https://openalex.org/W2418058303","https://openalex.org/W2438305798","https://openalex.org/W2550553598","https://openalex.org/W2551640181","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2743507428","https://openalex.org/W2745461083","https://openalex.org/W2951303555","https://openalex.org/W2962811161","https://openalex.org/W2963630207","https://openalex.org/W2963686907","https://openalex.org/W2964335273","https://openalex.org/W4214717370","https://openalex.org/W4237723258","https://openalex.org/W4254755460","https://openalex.org/W4294170691","https://openalex.org/W6600313631","https://openalex.org/W6631782140","https://openalex.org/W6639102338","https://openalex.org/W6656652561","https://openalex.org/W6677916085","https://openalex.org/W6682631176","https://openalex.org/W6714414533","https://openalex.org/W6729624334","https://openalex.org/W6746003159","https://openalex.org/W6749731246","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W2905654560","https://openalex.org/W2519434724","https://openalex.org/W3093267690","https://openalex.org/W4307074315","https://openalex.org/W2971866238"],"abstract_inverted_index":{"Image":[0],"captioning":[1,102],"and":[2,33,89,125],"visual":[3],"language":[4],"grounding":[5],"are":[6,14],"two":[7,43],"important":[8],"tasks":[9],"for":[10,37],"image":[11,31,55],"understanding,":[12],"but":[13],"seldom":[15],"considered":[16],"together.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,76],"Progressive":[24],"Attention-Guided":[25],"Network":[26],"(PAGNet),":[27],"which":[28,80],"simultaneously":[29],"generates":[30],"captions":[32],"predicts":[34],"bounding":[35,65,70],"boxes":[36,71],"caption":[38],"words.":[39],"PAGNet":[40,104,124,129],"mainly":[41],"has":[42],"distinctive":[44],"properties:":[45],"i)":[46],"It":[47,68],"can":[48],"progressively":[49],"refine":[50],"the":[51,59,63,73,82,96,101,107,111,121,131],"predictive":[52],"results":[53,126],"of":[54,72,84,110,123],"captioning,":[56],"by":[57],"updating":[58],"attention":[60,97],"map":[61,98],"with":[62],"predicted":[64],"boxes.":[66],"ii)":[67],"learns":[69],"words":[74],"using":[75,95],"weakly":[77],"supervised":[78],"strategy,":[79],"combines":[81],"frameworks":[83],"Multiple":[85],"Instance":[86],"Learning":[87],"(MIL)":[88],"Markov":[90],"Decision":[91],"Process":[92],"(MDP).":[93],"By":[94],"generated":[99],"in":[100],"process,":[103],"significantly":[105],"reduces":[106],"search":[108],"space":[109],"MDP.":[112],"We":[113],"conduct":[114],"experiments":[115],"on":[116],"benchmark":[117],"datasets":[118],"to":[119],"demonstrate":[120],"effectiveness":[122],"show":[127],"that":[128],"achieves":[130],"best":[132],"performance.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}