{"id":"https://openalex.org/W3209913752","doi":"https://doi.org/10.1145/3459637.3482383","title":"Relation Network and Causal Reasoning for Image Captioning","display_name":"Relation Network and Causal Reasoning for Image Captioning","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3209913752","doi":"https://doi.org/10.1145/3459637.3482383","mag":"3209913752"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069672411","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0003-0139-9415"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhou","raw_affiliation_strings":["Guangxi Normal University, GuiLin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University, GuiLin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101516308","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-7422-7297"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Guangxi Normal University, GuiLin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University, GuiLin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2718","last_page":"2727"},"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":0.9965000152587891,"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":0.989300012588501,"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/closed-captioning","display_name":"Closed captioning","score":0.9330579042434692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.803113579750061},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6618718504905701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5979300737380981},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5695180892944336},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5008792877197266},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4898914694786072},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4312405586242676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4008556604385376}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9330579042434692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803113579750061},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6618718504905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979300737380981},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5695180892944336},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5008792877197266},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4898914694786072},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4312405586242676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4008556604385376},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3744706737","display_name":"\u8054\u5408\u89c6\u89c9\u4e0e\u81ea\u7136\u8bed\u8a00\u7684\u7aef\u5230\u7aef\u884c\u4eba\u518d\u8fa8\u8bc6\u7814\u7a76","funder_award_id":"61866004","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2607151106","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2938260698","https://openalex.org/W2938603906","https://openalex.org/W2950275995","https://openalex.org/W2958442373","https://openalex.org/W2963115613","https://openalex.org/W2996202528","https://openalex.org/W2997591391","https://openalex.org/W2997848713","https://openalex.org/W2998409107","https://openalex.org/W2999653953","https://openalex.org/W3004561114","https://openalex.org/W3011574394","https://openalex.org/W3015437081","https://openalex.org/W3034984754","https://openalex.org/W3035160838","https://openalex.org/W3035323998","https://openalex.org/W3035512383","https://openalex.org/W3088409176","https://openalex.org/W3099726771","https://openalex.org/W3134272453","https://openalex.org/W3134428106","https://openalex.org/W3134991666","https://openalex.org/W3136792391","https://openalex.org/W3152581407","https://openalex.org/W3154766321","https://openalex.org/W3159583533","https://openalex.org/W3167939936","https://openalex.org/W3170494780","https://openalex.org/W3176470992","https://openalex.org/W3176689360","https://openalex.org/W3178322352","https://openalex.org/W3209574471"],"related_works":["https://openalex.org/W2795359650","https://openalex.org/W3107474891","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W4239686595","https://openalex.org/W4220800343","https://openalex.org/W3010872046","https://openalex.org/W2768413403","https://openalex.org/W2760085659","https://openalex.org/W2464179670"],"abstract_inverted_index":{"Image":[0],"captioning":[1,16,77],"is":[2,112,167],"a":[3,19,74,88,107,162],"cross-modal":[4],"problem":[5],"combining":[6],"computer":[7],"vision":[8],"and":[9,30,60,82,189],"natural":[10],"language":[11,65,156],"processing.":[12],"A":[13],"typical":[14],"image":[15,29,76,119,135],"model":[17,78,185,199],"uses":[18,32],"convolutional":[20],"neural":[21],"network":[22,37,59,91,95,111,124,157],"to":[23,38,96,114,153,169],"extract":[24],"the":[25,40,43,57,64,93,98,116,144,155,171,181,184,187,198],"features":[26],"of":[27,42,118,183],"an":[28,33,104,134],"then":[31],"Long":[34],"Short-Term":[35],"Memory":[36],"transform":[39],"representations":[41,128],"features.":[44],"However,":[45],"this":[46,71,202],"method":[47],"has":[48],"problems":[49],"such":[50],"as":[51,92,150],"not":[52],"including":[53],"high-level":[54,145],"semantics":[55,147],"in":[56,63,103,133,158,175,201],"visual":[58,94,141],"exposure":[61],"bias":[62],"network.":[66],"To":[67],"overcome":[68],"these":[69],"problems,":[70],"paper":[72,203],"proposes":[73],"novel":[75],"that":[79,197],"combines":[80],"relationship-aware":[81],"reinforcement":[83,176],"learning.":[84,177],"First,":[85],"we":[86],"design":[87],"relational":[89,110],"awareness":[90],"mine":[97],"latent":[99],"relationships":[100],"between":[101],"objects":[102],"image.":[105],"Then,":[106],"context":[108,122,146],"semantic":[109,123],"proposed":[113,200],"improve":[115],"accuracy":[117],"captioning.":[120],"The":[121,193],"can":[125],"generate":[126],"feature":[127],"for":[129],"arbitrary":[130],"pixel":[131],"positions":[132],"without":[136],"association":[137],"with":[138],"any":[139],"specific":[140],"concepts.":[142],"Subsequently,":[143],"are":[148],"used":[149],"external":[151],"knowledge":[152],"guide":[154],"generating":[159],"sentences.":[160],"Finally,":[161],"policy":[163],"gradient":[164],"training":[165],"algorithm":[166],"designed":[168],"simplify":[170],"state":[172],"value":[173],"function":[174],"We":[178],"have":[179],"verified":[180],"effectiveness":[182],"on":[186],"MS-COCO":[188],"Flickr":[190],"30K":[191],"datasets.":[192],"experimental":[194],"results":[195],"show":[196],"achieves":[204],"state-of-the-art":[205],"results.":[206]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}