{"id":"https://openalex.org/W3205607545","doi":"https://doi.org/10.1145/3474085.3475607","title":"Direction Relation Transformer for Image Captioning","display_name":"Direction Relation Transformer for Image Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205607545","doi":"https://doi.org/10.1145/3474085.3475607","mag":"3205607545"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5060506632","display_name":"Zeliang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Zeliang Song","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103179009","display_name":"Xiaofei Zhou","orcid":"https://orcid.org/0000-0001-9354-1209"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Xiaofei Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078405897","display_name":"Linhua Dong","orcid":"https://orcid.org/0000-0003-2344-6892"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Linhua Dong","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100533815","display_name":"Jianlong Tan","orcid":"https://orcid.org/0009-0001-4558-560X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Jianlong Tan","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675165","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-9723-3294"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Li Guo","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0375,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88867921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5056","last_page":"5064"},"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":0.9959999918937683,"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":0.9872000217437744,"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":0.8733295202255249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971773147583008},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7058624625205994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.604175865650177},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5955387353897095},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49503201246261597},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47859546542167664},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4677935242652893},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3485342860221863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3329029679298401},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08296611905097961}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8733295202255249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971773147583008},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7058624625205994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.604175865650177},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5955387353897095},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49503201246261597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47859546542167664},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4677935242652893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3485342860221863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3329029679298401},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08296611905097961},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/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":1,"locations":[{"id":"doi:10.1145/3474085.3475607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2950178297","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964308564","https://openalex.org/W2965697393","https://openalex.org/W2968549119","https://openalex.org/W2971310675","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2990818246","https://openalex.org/W3000433013","https://openalex.org/W3008309525","https://openalex.org/W3011702232","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3093088671","https://openalex.org/W3093374703","https://openalex.org/W3103237788","https://openalex.org/W3124043039","https://openalex.org/W3157142192","https://openalex.org/W3177244742"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4323777661","https://openalex.org/W4388184981"],"abstract_inverted_index":{"Image":[0],"captioning":[1,156],"is":[2,40],"a":[3,16,57,91],"challenging":[4,152],"task":[5],"that":[6],"combines":[7],"computer":[8],"vision":[9],"and":[10,81,131,160],"natural":[11],"language":[12],"processing":[13],"for":[14],"generating":[15],"textual":[17],"description":[18],"of":[19,59,127,136],"the":[20,44,63,73,79,98,106,118,124,128,142,167,197],"content":[21],"within":[22],"an":[23],"image.":[24],"Recently,":[25],"Transformer-based":[26],"encoder-decoder":[27],"architectures":[28],"have":[29],"shown":[30],"great":[31],"success":[32],"in":[33,78],"image":[34,80,155],"captioning,":[35],"where":[36],"multi-head":[37,111,138],"attention":[38,139],"mechanism":[39],"utilized":[41],"to":[42,71,96,123,140,194],"capture":[43],"contextual":[45],"interactions":[46],"between":[47,66,76,101],"object":[48,129],"regions.":[49],"However,":[50],"such":[51],"methods":[52],"regard":[53],"region":[54],"features":[55,103],"as":[56],"bag":[58],"tokens":[60],"without":[61],"considering":[62],"directional":[64,169],"relationships":[65],"them,":[67],"making":[68],"it":[69],"hard":[70],"understand":[72],"relative":[74,107,119,168],"position":[75],"objects":[77],"generate":[82,117],"correct":[83],"captions":[84],"effectively.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"novel":[92],"Direction":[93],"Relation":[94],"Transformer":[95,146],"improve":[97],"orientation":[99],"perception":[100],"visual":[102],"by":[104,165],"incorporating":[105],"direction":[108,120,143],"embedding":[109,144],"into":[110,145],"attention,":[112],"termed":[113],"DRT.":[114],"We":[115,148],"first":[116],"matrix":[121],"according":[122],"positional":[125],"information":[126],"regions,":[130],"then":[132],"explore":[133],"three":[134],"forms":[135],"direction-aware":[137],"integrate":[141],"architecture.":[147],"conduct":[149],"experiments":[150],"on":[151,196],"Microsoft":[153],"COCO":[154],"benchmark.":[157],"The":[158],"quantitative":[159],"qualitative":[161],"results":[162],"demonstrate":[163],"that,":[164],"integrating":[166],"relation,":[170],"our":[171],"proposed":[172],"approach":[173],"achieves":[174],"significant":[175],"improvements":[176],"over":[177],"all":[178],"evaluation":[179],"metrics":[180],"compared":[181],"with":[182],"baseline":[183],"model,":[184],"e.g.,":[185],"DRT":[186],"improves":[187],"task-specific":[188],"metric":[189],"CIDEr":[190],"score":[191],"from":[192],"129.7%":[193],"133.2%":[195],"offline":[198],"''Karpathy''":[199],"test":[200],"split.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}