{"id":"https://openalex.org/W4372260566","doi":"https://doi.org/10.1109/icassp49357.2023.10096823","title":"Spatial Cross-Attention for Transformer-Based Image Captioning","display_name":"Spatial Cross-Attention for Transformer-Based Image Captioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260566","doi":"https://doi.org/10.1109/icassp49357.2023.10096823"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025182785","display_name":"Khoa Anh Ngo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Khoa Anh Ngo","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Korea","Department of Electrical and Computer Engineering, Seoul National University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064051041","display_name":"Kyuhong Shim","orcid":"https://orcid.org/0000-0002-0123-3100"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuhong Shim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Korea","Department of Electrical and Computer Engineering, Seoul National University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076075267","display_name":"Byonghyo Shim","orcid":"https://orcid.org/0000-0001-5051-1763"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byonghyo Shim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Korea","Department of Electrical and Computer Engineering, Seoul National University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.3333,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56465332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"5"},"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":0.9976000189781189,"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":0.9952999949455261,"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":0.9204646348953247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820085346698761},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7097824811935425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352132320404053},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5293750762939453},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48591867089271545},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4651907980442047},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4413042962551117},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43246525526046753},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3278391361236572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32576853036880493},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07896110415458679},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06987613439559937}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9204646348953247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820085346698761},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7097824811935425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352132320404053},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5293750762939453},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48591867089271545},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4651907980442047},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4413042962551117},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43246525526046753},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3278391361236572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32576853036880493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07896110415458679},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06987613439559937},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.4099999964237213,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2105673573","https://openalex.org/W2133459682","https://openalex.org/W2506483933","https://openalex.org/W2962784628","https://openalex.org/W2963084599","https://openalex.org/W3005983418","https://openalex.org/W3124149278","https://openalex.org/W3134428106","https://openalex.org/W4212774754","https://openalex.org/W4220731687","https://openalex.org/W4281633595","https://openalex.org/W4287777632","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6638575559","https://openalex.org/W6639102338","https://openalex.org/W6639809013","https://openalex.org/W6641064462","https://openalex.org/W6682631176","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6777481484","https://openalex.org/W6789705400","https://openalex.org/W6839015040","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W3217195652","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Transformer-based":[0],"networks":[1],"have":[2],"achieved":[3],"great":[4],"success":[5],"in":[6,37,96],"image":[7,17,77],"captioning":[8],"because":[9],"of":[10,41,106,130,136],"the":[11,23,33,56,89,118,127,141,146],"attention":[12,109],"mechanism":[13],"that":[14,48,53,68,117],"finds":[15],"relevant":[16,76],"locations":[18],"for":[19],"each":[20],"word.":[21],"However,":[22],"current":[24],"cross-attention":[25,66,84,121],"process,":[26],"which":[27],"aligns":[28],"word-to-image,":[29],"does":[30],"not":[31],"consider":[32],"spatial":[34,42,70,94,108,120,128],"relationships":[35,95,129],"existing":[36],"patch-to-patch.":[38],"This":[39],"lack":[40],"information":[43,71],"may":[44],"cause":[45],"incorrect":[46],"descriptions":[47],"fail":[49],"at":[50],"generating":[51],"words":[52],"correctly":[54,125],"describe":[55,126],"positional":[57],"relationships.":[58],"In":[59,79,99],"this":[60],"paper,":[61],"we":[62,101],"introduce":[63,102],"a":[64],"novel":[65],"architecture":[67],"utilizes":[69],"from":[72],"coordinate":[73],"differences":[74],"between":[75],"patches.":[78],"doing":[80],"so,":[81],"our":[82],"new":[83],"process":[85],"dynamically":[86],"considers":[87],"both":[88],"related":[90],"contents":[91],"and":[92],"their":[93],"caption":[97],"generation.":[98],"addition,":[100],"an":[103,134],"efficient":[104],"implementation":[105],"relative":[107],"based":[110],"on":[111,140],"convolutional":[112],"operations.":[113],"Experimental":[114],"results":[115],"show":[116],"proposed":[119],"improves":[122],"captions":[123],"to":[124,133,145],"objects,":[131],"leading":[132],"increase":[135],"0.7":[137],"CIDEr":[138],"score":[139],"MS-COCO":[142],"dataset":[143],"compared":[144],"previous":[147],"state-of-the-art.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}