{"id":"https://openalex.org/W4377244980","doi":"https://doi.org/10.1145/3597613","title":"Self-supervised Multi-view Learning via Auto-encoding 3D Transformations","display_name":"Self-supervised Multi-view Learning via Auto-encoding 3D Transformations","publication_year":2023,"publication_date":"2023-05-22","ids":{"openalex":"https://openalex.org/W4377244980","doi":"https://doi.org/10.1145/3597613"},"language":"en","primary_location":{"id":"doi:10.1145/3597613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597613","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3597613","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076848346","display_name":"Xiang Gao","orcid":"https://orcid.org/0000-0002-2679-4019"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Gao","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-2679-4019","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059045087","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-9860-0922"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-9860-0922","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo-Jun Qi","raw_affiliation_strings":["OPPO US Research Center, United States"],"raw_orcid":"https://orcid.org/0000-0003-3508-1851","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3877,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53613853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.7528420090675354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.719555139541626},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6553249955177307},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.61497563123703},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5929117798805237},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5859354734420776},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5737215280532837},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5496309399604797},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.540431022644043},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4744766056537628},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4689345359802246},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.460247665643692},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39080023765563965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14142805337905884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11222505569458008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528420090675354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.719555139541626},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6553249955177307},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.61497563123703},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5929117798805237},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5859354734420776},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5737215280532837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5496309399604797},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.540431022644043},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4744766056537628},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4689345359802246},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.460247665643692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39080023765563965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14142805337905884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11222505569458008},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597613","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3597613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597613","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3604809996","display_name":"\u57fa\u4e8e\u8c31\u56fe\u7406\u8bba\u7684\u591a\u5206\u8fa8\u7387\u56fe\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u7814\u7a76","funder_award_id":"61972009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5265481717","display_name":null,"funder_award_id":"2021YFF0901502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377244980.pdf","grobid_xml":"https://content.openalex.org/works/W4377244980.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W2044738244","https://openalex.org/W2097117768","https://openalex.org/W2190691619","https://openalex.org/W2194775991","https://openalex.org/W2648403730","https://openalex.org/W2850910281","https://openalex.org/W2890018557","https://openalex.org/W2921891839","https://openalex.org/W2949690155","https://openalex.org/W2963173190","https://openalex.org/W2963231572","https://openalex.org/W2963312728","https://openalex.org/W2964253930","https://openalex.org/W2979750740","https://openalex.org/W3009238340","https://openalex.org/W3009561768","https://openalex.org/W3035524453","https://openalex.org/W3035725276","https://openalex.org/W3039448353","https://openalex.org/W3092095626","https://openalex.org/W3122063749","https://openalex.org/W3142707146","https://openalex.org/W3143835353","https://openalex.org/W3164387584","https://openalex.org/W3173768697","https://openalex.org/W3183682375","https://openalex.org/W3186139152","https://openalex.org/W3205003715","https://openalex.org/W4246329541","https://openalex.org/W4311415873","https://openalex.org/W4320013936","https://openalex.org/W4394671432","https://openalex.org/W6771790678"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"3D":[0,15,27,103,117,121,145,150,180],"object":[1,28,104,122,146,181],"representation":[2,138,147],"learning":[3,21,41,70],"is":[4,48,195],"a":[5,52,58,86,102,116,120,137],"fundamental":[6],"challenge":[7],"in":[8,19,26,45,51,179],"computer":[9],"vision":[10],"to":[11,72,90,141,190],"infer":[12],"about":[13],"the":[14,98,130,143,154,164,170,175,188],"world.":[16],"Recent":[17],"advances":[18],"deep":[20],"have":[22,34],"shown":[23],"their":[24],"efficiency":[25],"recognition,":[29],"among":[30],"which":[31,55],"view-based":[32,177],"methods":[33,47],"performed":[35,50],"best":[36],"so":[37],"far.":[38],"However,":[39],"feature":[40,75,156],"of":[42,61,101,158],"multiple":[43,108,125,159],"views":[44,109,126,160],"existing":[46],"mostly":[49],"supervised":[53],"fashion,":[54],"often":[56],"requires":[57],"large":[59],"amount":[60],"data":[62],"labels":[63],"with":[64],"high":[65],"costs.":[66],"In":[67],"contrast,":[68],"self-supervised":[69,88],"aims":[71],"learn":[73,91],"multi-view":[74],"representations":[76,157],"without":[77],"involving":[78],"labeled":[79],"data.":[80],"To":[81],"this":[82],"end,":[83],"we":[84,111,114,135],"propose":[85],"novel":[87],"framework":[89],"Multi-View":[92],"Transformation":[93],"Equivariant":[94],"Representations":[95],"(MV-TER),":[96],"exploring":[97],"equivariant":[99],"transformations":[100],"and":[105,123,128,162,183,186],"its":[106],"projected":[107],"that":[110,169],"derive.":[112],"Specifically,":[113],"perform":[115],"transformation":[118,131,151],"on":[119],"obtain":[124],"before":[127,161],"after":[129,163],"via":[132],"projection.":[133],"Then,":[134],"train":[136],"encoding":[139],"module":[140],"capture":[142],"intrinsic":[144],"by":[148],"decoding":[149],"parameters":[152],"from":[153],"fused":[155],"transformation.":[165],"Experimental":[166],"results":[167],"demonstrate":[168],"proposed":[171],"MV-TER":[172],"significantly":[173],"outperforms":[174],"state-of-the-art":[176],"approaches":[178],"classification":[182],"retrieval":[184],"tasks":[185],"show":[187],"generalization":[189],"real-world":[191],"datasets.":[192],"The":[193],"code":[194],"available":[196],"at":[197],"https://github.com/gyshgx868/mvter":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}