{"id":"https://openalex.org/W4415407719","doi":"https://doi.org/10.3233/faia250859","title":"Learning to Suppress Backgrounds and Bidirectionally Fuse Modalities for RGB-D Gesture Recognition","display_name":"Learning to Suppress Backgrounds and Bidirectionally Fuse Modalities for RGB-D Gesture Recognition","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415407719","doi":"https://doi.org/10.3233/faia250859"},"language":null,"primary_location":{"id":"doi:10.3233/faia250859","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250859","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250859","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067347622","display_name":"Xin Hu","orcid":"https://orcid.org/0000-0001-8113-8631"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Hu","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044422446","display_name":"Yunan Li","orcid":"https://orcid.org/0000-0001-7316-4354"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunan Li","raw_affiliation_strings":["Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103526490","display_name":"Yulang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulang Xu","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758235","display_name":"Yilin Zhang","orcid":"https://orcid.org/0000-0002-7059-2553"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032115074","display_name":"Zixiang Lu","orcid":"https://orcid.org/0000-0003-2743-2017"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiang Lu","raw_affiliation_strings":["Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007404362","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0002-2872-388X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","School of Computer Science and Technology, Xidian University, China","Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067347622"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64306152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994000196456909,"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":0.9994000196456909,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7120000123977661},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.5877000093460083},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5016000270843506},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5009999871253967},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4740999937057495},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4650000035762787},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43849998712539673},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3955000042915344},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.38749998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949000000953674},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7120000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302000284194946},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.5877000093460083},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.28060001134872437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250859","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250859","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250859","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250859","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"RGB-D":[0,68,134,148],"video-based":[1],"gesture":[2,69,135,149],"recognition":[3,70,162],"is":[4,166],"a":[5,65,79],"fundamental":[6],"task":[7],"in":[8,56,161],"computer":[9],"vision,":[10],"yet":[11],"it":[12],"remains":[13],"challenging":[14],"due":[15],"to":[16,34,52,89],"the":[17,24,43,138,152],"small":[18],"size":[19],"of":[20,26,46,140,154],"hand":[21],"regions":[22],"and":[23,40,48,78,93,119,157],"presence":[25],"redundant":[27],"background":[28,38,103],"noise.":[29],"Existing":[30],"methods":[31],"often":[32],"fail":[33],"effectively":[35],"suppress":[36],"irrelevant":[37,102],"features":[39,121],"inadequately":[41],"exploit":[42],"complementary":[44],"nature":[45],"RGB":[47,118],"depth":[49,120],"modalities,":[50],"leading":[51],"suboptimal":[53],"semantic":[54,127],"alignment":[55],"feature":[57],"fusion.":[58],"To":[59],"address":[60],"these":[61],"issues,":[62],"we":[63],"propose":[64],"novel":[66],"end-to-end":[67],"framework":[71],"that":[72],"incorporates":[73],"Spatiotemporal":[74],"Background":[75],"Suppression":[76],"(STBS)":[77],"Bidirectional":[80],"Modality":[81],"Fusion":[82],"Adapter":[83],"(BMFA).":[84],"STBS":[85],"leverages":[86],"Vision":[87],"Transformers":[88],"construct":[90],"region-wise":[91],"tokens":[92],"adaptively":[94],"merges":[95],"them":[96],"based":[97],"on":[98,131,145],"responses":[99],"scores,":[100],"suppressing":[101],"content":[104],"while":[105],"preserving":[106],"fine-grained":[107],"gesture-related":[108],"spatiotemporal":[109],"features.":[110],"Meanwhile,":[111],"BMFA":[112],"enables":[113],"deep,":[114],"bidirectional":[115],"interaction":[116],"between":[117],"across":[122],"encoder":[123],"layers,":[124],"enhancing":[125],"cross-modal":[126],"consistency.":[128],"Extensive":[129],"experiments":[130],"three":[132,146],"public":[133,147],"datasets":[136,150],"validate":[137,151],"effectiveness":[139,153],"our":[141,155],"method.":[142],"Experiments":[143],"conducted":[144],"approach":[156],"demonstrate":[158],"significant":[159],"improvements":[160],"performance.":[163],"Our":[164],"code":[165],"available":[167],"at":[168],"https://github.com/caicai211/SB-BFM":[169]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-22T00:00:00"}