{"id":"https://openalex.org/W4281931222","doi":"https://doi.org/10.1145/3512527.3531359","title":"3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation","display_name":"3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4281931222","doi":"https://doi.org/10.1145/3512527.3531359"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5065782705","display_name":"Zhidan Liu","orcid":"https://orcid.org/0000-0002-0211-877X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidan Liu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079555419","display_name":"Zhen Xing","orcid":"https://orcid.org/0000-0001-6407-0321"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xing","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046420009","display_name":"Xiangdong Zhou","orcid":"https://orcid.org/0000-0002-5538-7367"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Zhou","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016341475","display_name":"Yijiang Chen","orcid":"https://orcid.org/0000-0001-9727-8305"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijiang Chen","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019081550","display_name":"Guichun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guichun Zhou","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"508","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7563620805740356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7181718349456787},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6919313073158264},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6041250228881836},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5973191261291504},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5893157124519348},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5718247294425964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5612577795982361},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5297062397003174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5062107443809509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4472726285457611},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35286223888397217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563620805740356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7181718349456787},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6919313073158264},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6041250228881836},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5973191261291504},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5893157124519348},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5718247294425964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5612577795982361},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5297062397003174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5062107443809509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4472726285457611},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35286223888397217},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W753847829","https://openalex.org/W1591870335","https://openalex.org/W1949483711","https://openalex.org/W1991264156","https://openalex.org/W2011792403","https://openalex.org/W2108598243","https://openalex.org/W2138621090","https://openalex.org/W2194775991","https://openalex.org/W2200124539","https://openalex.org/W2344474200","https://openalex.org/W2519379752","https://openalex.org/W2560544142","https://openalex.org/W2560662850","https://openalex.org/W2565639579","https://openalex.org/W2600447016","https://openalex.org/W2795096917","https://openalex.org/W2798991696","https://openalex.org/W2799123546","https://openalex.org/W2962748819","https://openalex.org/W2962756421","https://openalex.org/W2962988048","https://openalex.org/W2963140444","https://openalex.org/W2963217716","https://openalex.org/W2963892972","https://openalex.org/W2972211064","https://openalex.org/W2981390381","https://openalex.org/W2982157312","https://openalex.org/W2987861506","https://openalex.org/W2988766935","https://openalex.org/W2993195924","https://openalex.org/W3011205600","https://openalex.org/W3034499993","https://openalex.org/W3034712732","https://openalex.org/W3037309139","https://openalex.org/W3090584485","https://openalex.org/W3101066076","https://openalex.org/W3103542727","https://openalex.org/W3107730598","https://openalex.org/W3110528336","https://openalex.org/W3112889778","https://openalex.org/W3118723758","https://openalex.org/W3176463841","https://openalex.org/W3186660190","https://openalex.org/W3190537575","https://openalex.org/W3196689140","https://openalex.org/W3197937825","https://openalex.org/W3204659849","https://openalex.org/W3209386620"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2123263858","https://openalex.org/W1834370135"],"abstract_inverted_index":{"Image-based":[0],"object":[1,13,84],"pose":[2,85],"estimation":[3,86],"sounds":[4],"amazing":[5],"because":[6],"in":[7,36,44,54,64],"real":[8],"applications":[9],"the":[10,52,65,69,77,124,167],"shape":[11,34,61],"of":[12,79,128,169],"is":[14,27,62,71],"oftentimes":[15],"not":[16,19],"available":[17],"or":[18],"easy":[20],"to":[21,30,115,136,160],"take":[22],"like":[23,42],"photos.":[24],"Although":[25],"it":[26],"an":[28,116,133],"advantage":[29],"some":[31],"extent,":[32],"un-explored":[33],"information":[35],"3D":[37,60,89],"vision":[38],"learning":[39,122],"problem":[40,53],"looks":[41],"\"flaws":[43],"jade''.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,97],"deal":[50],"with":[51,150],"a":[55,93,99,112,156],"reasonable":[56],"new":[57],"setting,":[58],"namely":[59],"exploited":[63],"training":[66,126],"process,":[67],"and":[68],"testing":[70],"still":[72],"purely":[73],"image-based.":[74],"We":[75,119,144],"enhance":[76],"performance":[78],"image-based":[80,117,153],"methods":[81,154],"for":[82,141],"category-agnostic":[83,152],"by":[87,92,155],"exploiting":[88],"knowledge":[90,102,129],"learned":[91],"multi-modal":[94,113],"method.":[95,171],"Specifically,":[96],"propose":[98],"novel":[100],"contrastive":[101,121],"distillation":[103],"framework":[104],"that":[105],"effectively":[106],"transfers":[107],"3D-augmented":[108],"image":[109],"representation":[110],"from":[111],"model":[114],"model.":[118],"integrate":[120],"into":[123],"two-stage":[125],"procedure":[127],"distillation,":[130],"which":[131],"formulates":[132],"advanced":[134],"solution":[135],"combine":[137],"these":[138],"two":[139],"approaches":[140],"cross-modal":[142],"tasks.":[143],"experimentally":[145],"report":[146],"state-of-the-art":[147],"results":[148],"compared":[149],"existing":[151],"large":[157],"margin":[158],"(up":[159],"+5%":[161],"improvement":[162],"on":[163],"ObjectNet3D":[164],"dataset),":[165],"demonstrating":[166],"effectiveness":[168],"our":[170]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}