{"id":"https://openalex.org/W4402915557","doi":"https://doi.org/10.1109/icip51287.2024.10648021","title":"Exploring Attention Mechanisms in Integration of Multi-Modal Information for Sign Language Recognition and Translation","display_name":"Exploring Attention Mechanisms in Integration of Multi-Modal Information for Sign Language Recognition and Translation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915557","doi":"https://doi.org/10.1109/icip51287.2024.10648021"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10648021","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10648021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5081902603","display_name":"Zaber Ibn Abdul Hakim","orcid":null},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Zaber Ibn Abdul Hakim","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092829335","display_name":"Rasman Mubtasim Swargo","orcid":null},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Rasman Mubtasim Swargo","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059669108","display_name":"Muhammad Abdullah Adnan","orcid":"https://orcid.org/0000-0003-3219-9053"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Adnan","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET),Dhaka,Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183697816"],"apc_list":null,"apc_paid":null,"fwci":1.0905,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76685731,"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":"2529","last_page":"2535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11285","display_name":"Hearing Impairment and Communication","score":0.926800012588501,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421356439590454},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6192275285720825},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6014705896377563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5337881445884705},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.46996113657951355},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.44920220971107483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44000160694122314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3379017114639282},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3195015490055084},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08020845055580139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07054182887077332},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05518019199371338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421356439590454},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6192275285720825},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6014705896377563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5337881445884705},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.46996113657951355},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.44920220971107483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44000160694122314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3379017114639282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3195015490055084},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08020845055580139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07054182887077332},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05518019199371338},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10648021","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10648021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325821","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2560474170","https://openalex.org/W2799020610","https://openalex.org/W2895638065","https://openalex.org/W2908497602","https://openalex.org/W2948139159","https://openalex.org/W2954798773","https://openalex.org/W2997931247","https://openalex.org/W3024468270","https://openalex.org/W3034765865","https://openalex.org/W3092363664","https://openalex.org/W3124683025","https://openalex.org/W3126451397","https://openalex.org/W3147467731","https://openalex.org/W3184215204","https://openalex.org/W3198233388","https://openalex.org/W3201832684","https://openalex.org/W3202850984","https://openalex.org/W3203359574","https://openalex.org/W3204447181","https://openalex.org/W4312839448","https://openalex.org/W4312910375","https://openalex.org/W4367047590","https://openalex.org/W6691399679","https://openalex.org/W6691592925","https://openalex.org/W6751523092","https://openalex.org/W6846322403"],"related_works":["https://openalex.org/W2110143569","https://openalex.org/W3122938442","https://openalex.org/W4379621602","https://openalex.org/W4294690766","https://openalex.org/W2159815235","https://openalex.org/W3204710839","https://openalex.org/W2025206082","https://openalex.org/W2093958826","https://openalex.org/W2164424388","https://openalex.org/W1989687946"],"abstract_inverted_index":{"Understanding":[0],"intricate":[1],"and":[2,13,26,71,151,172],"fast-paced":[3],"movements":[4],"of":[5,15,20,96,131,140],"body":[6,30],"parts":[7,31],"is":[8,120],"essential":[9],"for":[10,100,147,155],"the":[11,28,56,94,109,132,138,144,152,156,164,169,174,181],"recognition":[12,150,170],"translation":[14,159,182],"sign":[16,148,157],"language.":[17],"The":[18],"inclusion":[19],"additional":[21,101,116],"information":[22,45],"intended":[23],"to":[24,79,82,92],"identify":[25],"locate":[27],"moving":[29],"has":[32],"been":[33],"an":[34,104],"interesting":[35],"research":[36],"topic":[37],"recently.":[38],"However,":[39],"previous":[40],"works":[41],"on":[42,77,129,143,168,180],"using":[43],"multi-modal":[44,51],"raise":[46],"concerns":[47],"such":[48,69],"as":[49],"sub-optimal":[50],"feature":[52,98],"merging":[53],"method,":[54],"or":[55],"model":[57],"itself":[58],"being":[59],"too":[60],"computationally":[61],"heavy.":[62],"In":[63],"our":[64,115,141],"work,":[65],"we":[66,88],"have":[67,136],"addressed":[68],"issues":[70],"used":[72],"a":[73],"plugin":[74,118],"module":[75,119],"based":[76],"cross-attention":[78,117],"properly":[80],"attend":[81],"each":[83],"modality":[84],"with":[85],"another.":[86],"Moreover,":[87],"utilized":[89],"2-stage":[90],"training":[91],"remove":[93],"dependency":[95],"separate":[97],"extractors":[99],"modalities":[102],"in":[103],"end-to-end":[105],"approach,":[106],"which":[107,123],"reduces":[108],"concern":[110],"about":[111],"computational":[112,127],"complexity.":[113],"Besides,":[114],"very":[121],"lightweight":[122],"doesn\u2019t":[124],"add":[125],"significant":[126],"overhead":[128],"top":[130],"original":[133],"baseline.":[134],"We":[135],"evaluated":[137],"performance":[139],"approaches":[142],"RWTH-PHOENIX-2014":[145],"dataset":[146,154],"language":[149,158],"RWTH-PHOENIX-2014T":[153],"task.":[160,183],"Our":[161],"approach":[162],"reduced":[163],"WER":[165],"by":[166,178],"0.9":[167],"task":[171],"increased":[173],"BLEU-":[175],"4":[176],"scores":[177],"0.8":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}