{"id":"https://openalex.org/W3002776425","doi":"https://doi.org/10.1109/robio49542.2019.8961665","title":"Positional Self-attention Based Hierarchical Image Captioning","display_name":"Positional Self-attention Based Hierarchical Image Captioning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3002776425","doi":"https://doi.org/10.1109/robio49542.2019.8961665","mag":"3002776425"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5023579469","display_name":"Qianxia Ma","orcid":"https://orcid.org/0000-0002-6635-2792"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxia Ma","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101444025","display_name":"Jingyan Song","orcid":"https://orcid.org/0000-0001-9790-8573"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyan Song","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375792","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-2980-6281"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"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":"1173","last_page":"1178"},"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":0.9993000030517578,"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":0.9966999888420105,"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":0.8755655288696289},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8436106443405151},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6426414251327515},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6211150288581848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6117842793464661},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5297202467918396},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5154286623001099},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49181678891181946},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4805186688899994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4764316976070404},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4243176579475403},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37012535333633423},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3353806138038635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33015120029449463},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10910224914550781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755655288696289},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8436106443405151},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6426414251327515},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6211150288581848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6117842793464661},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5297202467918396},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5154286623001099},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49181678891181946},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4805186688899994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4764316976070404},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4243176579475403},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37012535333633423},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3353806138038635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33015120029449463},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10910224914550781},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1687846465","https://openalex.org/W1745796331","https://openalex.org/W1858383477","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2109586012","https://openalex.org/W2114841702","https://openalex.org/W2126384256","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2149172860","https://openalex.org/W2157331557","https://openalex.org/W2159243025","https://openalex.org/W2171361956","https://openalex.org/W2339652278","https://openalex.org/W2423557781","https://openalex.org/W2481240925","https://openalex.org/W2552161745","https://openalex.org/W2567070169","https://openalex.org/W2613904329","https://openalex.org/W2619383789","https://openalex.org/W2788710361","https://openalex.org/W2963403868","https://openalex.org/W2963636093","https://openalex.org/W2963918688","https://openalex.org/W2963970792","https://openalex.org/W2964199361","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W4385245566","https://openalex.org/W6631516269","https://openalex.org/W6637306801","https://openalex.org/W6639118148","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6677231853","https://openalex.org/W6678712372","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682086108","https://openalex.org/W6683258052","https://openalex.org/W6683512859","https://openalex.org/W6684941089","https://openalex.org/W6685230081","https://openalex.org/W6704203392","https://openalex.org/W6725287029","https://openalex.org/W6729624334","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Intelligent":[0],"robotic":[1],"systems":[2],"process":[3],"images":[4],"captured":[5],"by":[6],"camera":[7],"devices":[8],"to":[9,43,62,81,94],"get":[10],"high-level":[11],"semantic":[12],"concepts.":[13],"Current":[14],"image":[15],"captioning":[16],"approaches":[17],"use":[18],"convolutional":[19,68],"neural":[20,26,56,69],"networks":[21,27,70],"as":[22,28],"encoder":[23],"and":[24,35,74],"recurrent":[25],"decoder.":[29],"Various":[30],"modalities":[31],"are":[32,71],"treated":[33],"differently":[34],"parallel":[36,54,106],"computation":[37],"is":[38,89],"not":[39],"fully":[40],"allowed":[41],"due":[42],"the":[44,75,92,96,123],"chain":[45],"architecture.":[46],"To":[47],"address":[48],"these":[49],"issues,":[50],"we":[51],"present":[52],"a":[53,118,128],"hierarchical":[55,76],"network":[57],"based":[58],"on":[59],"encoder-decoder":[60],"architecture":[61,113],"generate":[63],"descriptions":[64],"for":[65,105,114],"images.":[66],"Only":[67],"adopted":[72],"here,":[73],"framework":[77],"takes":[78],"less":[79],"steps":[80],"capture":[82],"distant":[83],"dependencies.":[84],"Masked":[85],"positional":[86],"self-attention":[87],"mechanism":[88],"utilized":[90],"in":[91],"decoder":[93],"improve":[95],"performance.":[97],"The":[98],"fixed":[99],"sized":[100],"windows":[101],"make":[102],"it":[103],"possible":[104],"computation.":[107],"This":[108],"generative":[109],"model":[110],"uses":[111],"unified":[112],"different":[115],"modalities,":[116],"reaching":[117],"BLEU-1":[119],"score":[120],"(the":[121],"higher":[122,129],"better)":[124],"over":[125],"0.7":[126],"with":[127],"training":[130],"speed.":[131]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}