{"id":"https://openalex.org/W2998637494","doi":"https://doi.org/10.1109/dicta47822.2019.8946003","title":"Bi-SAN-CAP: Bi-Directional Self-Attention for Image Captioning","display_name":"Bi-SAN-CAP: Bi-Directional Self-Attention for Image Captioning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2998637494","doi":"https://doi.org/10.1109/dicta47822.2019.8946003","mag":"2998637494"},"language":"en","primary_location":{"id":"doi:10.1109/dicta47822.2019.8946003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta47822.2019.8946003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","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/A5100681207","display_name":"Md Zakir Hossain","orcid":"https://orcid.org/0000-0003-1212-4652"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Md Zakir Hossain","raw_affiliation_strings":["College of Science, Health, Engineering and Education Murdoch University, Australia"],"affiliations":[{"raw_affiliation_string":"College of Science, Health, Engineering and Education Murdoch University, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002219416","display_name":"Ferdous Sohel","orcid":"https://orcid.org/0000-0003-1557-4907"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ferdous Sohel","raw_affiliation_strings":["College of Science, Health, Engineering and Education Murdoch University, Australia"],"affiliations":[{"raw_affiliation_string":"College of Science, Health, Engineering and Education Murdoch University, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014927373","display_name":"Mohd Fairuz Shiratuddin","orcid":"https://orcid.org/0000-0002-9529-6320"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohd Fairuz Shiratuddin","raw_affiliation_strings":["College of Science, Health, Engineering and Education Murdoch University, Australia"],"affiliations":[{"raw_affiliation_string":"College of Science, Health, Engineering and Education Murdoch University, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002077138","display_name":"Hamid Laga","orcid":"https://orcid.org/0000-0002-4758-7510"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hamid Laga","raw_affiliation_strings":["College of Science, Health, Engineering and Education Murdoch University, Australia"],"affiliations":[{"raw_affiliation_string":"College of Science, Health, Engineering and Education Murdoch University, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100681207"],"corresponding_institution_ids":["https://openalex.org/I176790772"],"apc_list":null,"apc_paid":null,"fwci":1.1244,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82821738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9966999888420105,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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":0.9798838496208191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8535232543945312},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6065114140510559},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5924621224403381},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5886067152023315},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.547663688659668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174092054367065},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49353325366973877},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.446952223777771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4309846758842468},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07446041703224182}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9798838496208191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535232543945312},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6065114140510559},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5924621224403381},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5886067152023315},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.547663688659668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174092054367065},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49353325366973877},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.446952223777771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4309846758842468},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07446041703224182},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dicta47822.2019.8946003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta47822.2019.8946003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/abfed7a4-8215-45f3-85af-f451ac7dcabe","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/abfed7a4-8215-45f3-85af-f451ac7dcabe","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hossain , M Z , Sohel , F , Shiratuddin , M F , Laga , H & Bennamoun , M 2019 , Bi-SAN-CAP : Bi-Directional Self-Attention for Image Captioning . in 2019 Digital Image Computing : Techniques and Applications, DICTA 2019 . , 8946003 , 2019 Digital Image Computing: Techniques and Applications, DICTA 2019 , IEEE, Institute of Electrical and Electronics Engineers , 2019 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2019 , Perth , Western Australia , Australia , 2/12/19 . https://doi.org/10.1109/DICTA47822.2019.8946003","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2282219577","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2423557781","https://openalex.org/W2540404261","https://openalex.org/W2559780844","https://openalex.org/W2575842049","https://openalex.org/W2604729005","https://openalex.org/W2613904329","https://openalex.org/W2740118378","https://openalex.org/W2786396726","https://openalex.org/W2800782462","https://openalex.org/W2801271919","https://openalex.org/W2803206166","https://openalex.org/W2803620531","https://openalex.org/W2885013662","https://openalex.org/W2887272576","https://openalex.org/W2896348597","https://openalex.org/W2902295951","https://openalex.org/W2950212751","https://openalex.org/W2951763382","https://openalex.org/W2962706528","https://openalex.org/W2963403868","https://openalex.org/W2963636093","https://openalex.org/W2963686907","https://openalex.org/W2964121744","https://openalex.org/W2964189376","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2964347512","https://openalex.org/W3100183449","https://openalex.org/W4301368689","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6729053843","https://openalex.org/W6736419893","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6748546225","https://openalex.org/W6752113587","https://openalex.org/W6756799292","https://openalex.org/W6898505805"],"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":{"In":[0,64],"a":[1,6],"typical":[2],"image":[3,15,38,113],"captioning":[4],"pipeline,":[5],"Convolutional":[7],"Neural":[8],"Network":[9],"(CNN)":[10],"is":[11,50,79],"used":[12],"as":[13,22],"the":[14,23,54,98,101],"encoder":[16],"and":[17,121],"Long":[18],"Short-Term":[19],"Memory":[20],"(LSTM)":[21],"language":[24],"decoder.":[25],"LSTM":[26,40,57],"with":[27],"attention":[28,91,106,117],"mechanism":[29,107],"has":[30],"shown":[31,73],"remarkable":[32],"performance":[33,127],"on":[34],"sequential":[35,46,62],"data":[36],"including":[37],"captioning.":[39,114],"can":[41],"retain":[42],"long-range":[43],"dependency":[44],"of":[45,56,59,100],"data.":[47],"However,":[48,87],"it":[49],"hard":[51],"to":[52,66,96,129],"parallelize":[53],"computations":[55],"because":[58],"its":[60],"inherent":[61],"characteristics.":[63],"order":[65],"address":[67],"this":[68],"issue,":[69],"recent":[70],"works":[71],"have":[72],"benefits":[74],"in":[75,93,119],"using":[76],"self-attention,":[77],"which":[78],"highly":[80],"parallelizable":[81],"without":[82],"requiring":[83],"any":[84],"temporal":[85],"dependencies.":[86],"existing":[88],"techniques":[89],"apply":[90],"only":[92],"one":[94],"direction":[95],"compute":[97],"context":[99],"words.":[102],"We":[103],"propose":[104],"an":[105],"called":[108],"Bi-directional":[109],"Self-Attention":[110],"(Bi-SAN)":[111],"for":[112],"It":[115,124],"computes":[116],"both":[118],"forward":[120],"backward":[122],"directions.":[123],"achieves":[125],"high":[126],"comparable":[128],"state-of-the-art":[130],"methods.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}