{"id":"https://openalex.org/W3201136692","doi":"https://doi.org/10.1109/tpami.2021.3113612","title":"Learning Spherical Convolution for 360 Recognition","display_name":"Learning Spherical Convolution for 360 Recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3201136692","doi":"https://doi.org/10.1109/tpami.2021.3113612","mag":"3201136692","pmid":"https://pubmed.ncbi.nlm.nih.gov/34543192"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3113612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3113612","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103041770","display_name":"Yu-Chuan Su","orcid":"https://orcid.org/0000-0002-2711-6738"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Chuan Su","raw_affiliation_strings":["Computer Science, University of Texas at Austin, 12330 Austin, Texas, United States, (e-mail: ycsu@utexas.edu)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Texas at Austin, 12330 Austin, Texas, United States, (e-mail: ycsu@utexas.edu)","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012765543","display_name":"Kristen Grauman","orcid":"https://orcid.org/0000-0002-9591-5873"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["AI Research, Facebook Inc, 342996 Menlo Park, California, United States, (e-mail: grauman@cs.utexas.edu)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research, Facebook Inc, 342996 Menlo Park, California, United States, (e-mail: grauman@cs.utexas.edu)","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6017,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85669694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"44","issue":"11","first_page":"1","last_page":"1"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.674148678779602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6311530470848083},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5874776840209961},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4628768265247345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46084973216056824},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4345611333847046},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34923750162124634},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24156609177589417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.674148678779602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6311530470848083},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5874776840209961},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4628768265247345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46084973216056824},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4345611333847046},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34923750162124634},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24156609177589417}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3113612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3113612","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34543192","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34543192","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5395344063","display_name":null,"funder_award_id":"IIS-1514118","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W566730006","https://openalex.org/W753847829","https://openalex.org/W1522734439","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2045556253","https://openalex.org/W2103189262","https://openalex.org/W2108598243","https://openalex.org/W2121169511","https://openalex.org/W2187966737","https://openalex.org/W2194775991","https://openalex.org/W2294370754","https://openalex.org/W2342662179","https://openalex.org/W2519882289","https://openalex.org/W2531409750","https://openalex.org/W2556362500","https://openalex.org/W2593745480","https://openalex.org/W2601564443","https://openalex.org/W2604274373","https://openalex.org/W2605344185","https://openalex.org/W2611836059","https://openalex.org/W2618530766","https://openalex.org/W2756065914","https://openalex.org/W2766258444","https://openalex.org/W2766306266","https://openalex.org/W2787091153","https://openalex.org/W2796422723","https://openalex.org/W2798665861","https://openalex.org/W2890636441","https://openalex.org/W2895640967","https://openalex.org/W2895696451","https://openalex.org/W2962965870","https://openalex.org/W2963339238","https://openalex.org/W2963363373","https://openalex.org/W2963389277","https://openalex.org/W2963691181","https://openalex.org/W2963866094","https://openalex.org/W2964306713","https://openalex.org/W2969261403","https://openalex.org/W4297775537","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6679909955","https://openalex.org/W6685726866","https://openalex.org/W6726275242","https://openalex.org/W6731028397","https://openalex.org/W6737664043","https://openalex.org/W6763349780","https://openalex.org/W6769516661"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2049538278","https://openalex.org/W2886173746","https://openalex.org/W2074736680"],"abstract_inverted_index":{"While":[0],"360":[1,23,78,96,108,206],"cameras":[2],"offer":[3],"tremendous":[4],"new":[5],"possibilities":[6],"in":[7,57,205],"vision,":[8],"graphics,":[9],"and":[10,104,110,136,159,175,191],"augmented":[11],"reality,":[12],"the":[13,27,74,91,112,134,149,167],"spherical":[14,49,185,198],"images":[15,50],"they":[16],"produce":[17],"make":[18],"visual":[19],"recognition":[20,106],"non-trivial.":[21],"Ideally,":[22],"imagery":[24],"could":[25],"inherit":[26],"convolutional":[28],"neural":[29],"networks":[30,117],"(CNNs)":[31],"trained":[32],"with":[33,155],"great":[34],"success":[35],"on":[36,95,133,189],"perspective":[37,47,85,119],"projection":[38,76],"images.":[39,79,120,207],"However,":[40],"existing":[41],"methods":[42],"to":[43,48,61,73,89,114,177],"transfer":[44],"CNNs":[45,158],"from":[46,148],"introduce":[51,183],"significant":[52],"computational":[53],"costs":[54],"and/or":[55],"degradations":[56],"accuracy.":[58],"We":[59,121,181],"propose":[60,122],"learn":[62,196],"a":[63,70,81,142,184,197],"Spherical":[64],"Convolution":[65],"Network":[66],"(SphConv)":[67],"that":[68,145,163,193],"translates":[69],"planar":[71],"CNN":[72,83],"equirectangular":[75],"of":[77,125],"Given":[80],"source":[82,150,157,168],"for":[84,107,118],"images,":[86,109],"SphConv":[87,147,190],"learns":[88,129,141],"reproduce":[90],"flat":[92],"filter":[93],"outputs":[94],"data.":[97],"The":[98],"key":[99],"benefits":[100],"are":[101],"1)":[102],"efficient":[103],"accurate":[105],"2)":[111],"ability":[113],"leverage":[115],"pre-trained":[116],"two":[123],"instantiations":[124],"SphConv---Spherical":[126],"Kernel,":[127],"which":[128,140],"location":[130],"dependent":[131],"kernels":[132],"sphere,":[135],"Kernel":[137],"Transformer":[138],"Network,":[139],"functional":[143],"transformation":[144],"generates":[146],"CNN.":[151],"Validating":[152],"our":[153],"approach":[154],"multiple":[156],"datasets,":[160],"we":[161,194],"show":[162,192],"it":[164],"successfully":[165],"preserves":[166],"CNN's":[169],"accuracy,":[170],"while":[171],"offering":[172],"efficiency,":[173],"transferability,":[174],"scalability":[176],"typical":[178],"image":[179],"resolutions.":[180],"further":[182],"Faster":[186],"R-CNN":[187],"based":[188],"can":[195],"object":[199,203],"detector":[200],"without":[201],"any":[202],"annotations":[204]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-09-27T00:00:00"}