{"id":"https://openalex.org/W4401991040","doi":"https://doi.org/10.1109/icmew63481.2024.10645396","title":"Learning to Learn Multiview Detection by Camera-Aware Attention","display_name":"Learning to Learn Multiview Detection by Camera-Aware Attention","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991040","doi":"https://doi.org/10.1109/icmew63481.2024.10645396"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645396","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645396","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 Multimedia and Expo Workshops (ICMEW)","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/A5023752828","display_name":"Hung-Min Hsu","orcid":"https://orcid.org/0000-0002-7180-1396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Min Hsu","raw_affiliation_strings":["WYZE Labs AI Team,Kirkland,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WYZE Labs AI Team,Kirkland,WA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087258613","display_name":"Zhongwei Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongwei Cheng","raw_affiliation_strings":["WYZE Labs AI Team,Kirkland,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WYZE Labs AI Team,Kirkland,WA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560430","display_name":"Xinyu Yuan","orcid":"https://orcid.org/0000-0002-7626-0111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Yuan","raw_affiliation_strings":["WYZE Labs AI Team,Kirkland,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WYZE Labs AI Team,Kirkland,WA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Lin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["WYZE Labs AI Team,Kirkland,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WYZE Labs AI Team,Kirkland,WA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9932000041007996,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9932000041007996,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9887999892234802,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7740230560302734},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6219802498817444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577784776687622},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3209291696548462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7740230560302734},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6219802498817444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577784776687622},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3209291696548462}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645396","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645396","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 Multimedia and Expo Workshops (ICMEW)","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":10,"referenced_works":["https://openalex.org/W2145680191","https://openalex.org/W2799108620","https://openalex.org/W2963859909","https://openalex.org/W3012573144","https://openalex.org/W3107147550","https://openalex.org/W3158982130","https://openalex.org/W3160359205","https://openalex.org/W3202890594","https://openalex.org/W3207737630","https://openalex.org/W4319300102"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Multiview":[0],"detection":[1,143],"task":[2],"is":[3,21,62],"to":[4,9,49,72,100,109,117,136],"utilize":[5],"multiple":[6,41],"camera":[7,77,115],"views":[8,116],"reduce":[10,118],"the":[11,14,16,22,35,46,65,102,119,138,141,149],"severity":[12],"of":[13,19,140],"occlusion,":[15],"critical":[17],"part":[18],"which":[20],"multiview":[23,103,134,142],"aggregation.":[24],"The":[25,145],"aggregated":[26],"ground":[27],"plane":[28],"feature":[29,37],"can":[30],"be":[31],"acquired":[32],"based":[33,87],"on":[34,152],"convolutional":[36],"map":[38],"projections":[39],"from":[40,52,59,113],"views,":[42],"and":[43,75,127],"it":[44],"uses":[45],"same":[47],"weight":[48],"fuse":[50],"information":[51,58,112,129],"all":[53,60],"cameras.":[54],"However,":[55],"di-rectly":[56],"using":[57],"cameras":[61],"suboptimal,":[63],"as":[64,91],"object":[66],"features":[67],"undergo":[68],"various":[69],"occlusions":[70],"according":[71],"their":[73],"positions":[74],"corresponding":[76],"perspectives.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"propose":[83],"a":[84,95],"novel":[85],"meta-learning":[86],"multi-view":[88],"detector,":[89],"dubbed":[90],"MetaMVDet,":[92],"that":[93],"adopts":[94],"newly":[96],"introduced":[97],"camera-aware":[98,106],"attention":[99,107],"aggregate":[101],"information.":[104],"Our":[105],"aims":[108],"select":[110],"reli-able":[111],"different":[114],"ambiguity":[120],"by":[121],"occlusions.":[122],"We":[123],"leverage":[124],"both":[125],"2D":[126],"3D":[128],"simultaneously":[130],"while":[131],"maintaining":[132],"2D-3D":[133],"consistency":[135],"guide":[137],"learning":[139],"network.":[144],"proposed":[146],"solution":[147],"achieves":[148],"state-of-the-art":[150],"accuracy":[151],"two":[153],"major":[154],"multiview-detection":[155],"benchmarks.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}