{"id":"https://openalex.org/W2903617461","doi":"https://doi.org/10.1609/aaai.v33i01.33018650","title":"Learning Object Context for Dense Captioning","display_name":"Learning Object Context for Dense Captioning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903617461","doi":"https://doi.org/10.1609/aaai.v33i01.33018650","mag":"2903617461"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018650","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4886/4759","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/4886/4759","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341799","display_name":"Xiangyang Li","orcid":"https://orcid.org/0000-0002-3944-4704"},"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":"Xiangyang Li","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"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":"Shuqiang Jiang","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"8650","last_page":"8657"},"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/T10812","display_name":"Human Pose and Action Recognition","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9937999844551086,"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":0.8455876111984253},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8281165361404419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6554721593856812},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6017622351646423},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5863551497459412},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5659159421920776},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5233913064002991},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5191622972488403},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49811625480651855},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4898078143596649},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.42183348536491394},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3950803875923157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34302660822868347},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1759510040283203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455876111984253},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8281165361404419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6554721593856812},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6017622351646423},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5863551497459412},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5659159421920776},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5233913064002991},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5191622972488403},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49811625480651855},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4898078143596649},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.42183348536491394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3950803875923157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34302660822868347},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1759510040283203},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018650","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4886/4759","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/4886","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4886","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.v33i01.33018650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018650","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4886/4759","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":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3605299792","display_name":"\u8de8\u7f51\u4e92\u8054\u89c6\u97f3\u9891\u5173\u8054\u5206\u6790\u4e0e\u641c\u7d22","funder_award_id":"61532018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903617461.pdf","grobid_xml":"https://content.openalex.org/works/W2903617461.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W1514535095","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1905882502","https://openalex.org/W2050482109","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2133512280","https://openalex.org/W2163605009","https://openalex.org/W2179022885","https://openalex.org/W2194775991","https://openalex.org/W2254252455","https://openalex.org/W2277195237","https://openalex.org/W2288122362","https://openalex.org/W2552002300","https://openalex.org/W2558834163","https://openalex.org/W2560313346","https://openalex.org/W2564898401","https://openalex.org/W2579549467","https://openalex.org/W2606609115","https://openalex.org/W2613718673","https://openalex.org/W2618530766","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2756246624","https://openalex.org/W2787090809","https://openalex.org/W2790600496","https://openalex.org/W2953106684","https://openalex.org/W2963037989","https://openalex.org/W2963084599","https://openalex.org/W2963191264","https://openalex.org/W2963420686","https://openalex.org/W2963448089","https://openalex.org/W2963649796","https://openalex.org/W2963758027","https://openalex.org/W2963923113","https://openalex.org/W2964080601","https://openalex.org/W3106250896","https://openalex.org/W3122775348","https://openalex.org/W4309845474","https://openalex.org/W6631782140","https://openalex.org/W6662717790","https://openalex.org/W6687483927","https://openalex.org/W6732298944","https://openalex.org/W6743731764","https://openalex.org/W6746975906","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Dense":[0],"captioning":[1],"is":[2,180],"a":[3,76,104,140],"challenging":[4],"task":[5],"which":[6],"not":[7,26,84],"only":[8,85],"detects":[9],"visual":[10],"elements":[11],"in":[12,30,96,181],"images":[13,31],"but":[14,89],"also":[15,70,90],"generates":[16],"natural":[17],"language":[18],"sentences":[19],"to":[20,40,117,131,150,166,200],"describe":[21],"them.":[22],"Previous":[23],"approaches":[24],"do":[25],"leverage":[27],"object":[28,109,121,158,196,205],"information":[29,73],"for":[32,74,123],"this":[33,100],"task.":[34],"However,":[35],"objects":[36,55,63,69,95,130,136],"provide":[37,71],"valuable":[38],"cues":[39],"help":[41],"predict":[42,167],"the":[43,81,97,146,156,168,174,184,195,212,219],"locations":[44],"of":[45,62,66,186,214],"caption":[46,49,57,78,125,132,191],"regions":[47,50,58],"as":[48,80,139],"often":[51],"highly":[52],"overlap":[53],"with":[54,94,107,183],"(i.e.":[56],"are":[59,137,164],"usually":[60],"parts":[61],"or":[64],"combinations":[65],"them).":[67],"Meanwhile,":[68],"important":[72],"describing":[75],"target":[77],"region":[79,162],"corresponding":[82],"description":[83],"depicts":[86],"its":[87,92],"properties,":[88],"involves":[91],"interactions":[93],"image.":[98],"In":[99],"work,":[101],"we":[102],"propose":[103],"novel":[105],"scheme":[106],"an":[108],"context":[110,122,147,152,159,177,197],"encoding":[111,148,198],"Long":[112],"Short-Term":[113],"Memory":[114],"(LSTM)":[115],"network":[116],"automatically":[118],"learn":[119],"complementary":[120],"each":[124],"region,":[126],"transferring":[127],"knowledge":[128],"from":[129],"regions.":[133],"All":[134],"contextual":[135],"arranged":[138],"sequence":[141],"and":[142,161,172,190,202],"progressively":[143],"fed":[144],"into":[145],"module":[149],"obtain":[151],"features.":[153],"Then":[154],"both":[155,187],"learned":[157],"features":[160,163],"used":[165],"bounding":[169],"box":[170],"offsets":[171],"generate":[173],"descriptions.":[175],"The":[176],"learning":[178],"procedure":[179],"conjunction":[182],"optimization":[185],"location":[188],"prediction":[189],"generation,":[192],"thus":[193],"enabling":[194],"LSTM":[199],"capture":[201],"aggregate":[203],"useful":[204],"context.":[206],"Experiments":[207],"on":[208],"benchmark":[209],"datasets":[210],"demonstrate":[211],"superiority":[213],"our":[215],"proposed":[216],"approach":[217],"over":[218],"state-of-the-art":[220],"methods.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}