{"id":"https://openalex.org/W4304091582","doi":"https://doi.org/10.1145/3503161.3547956","title":"Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space","display_name":"Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091582","doi":"https://doi.org/10.1145/3503161.3547956"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547956","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5057245138","display_name":"Lingwei Dang","orcid":"https://orcid.org/0000-0003-3825-8894"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingwei Dang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083221103","display_name":"Yongwei Nie","orcid":"https://orcid.org/0000-0002-8922-3205"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Nie","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027540915","display_name":"Chengjiang Long","orcid":"https://orcid.org/0000-0003-1584-7290"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengjiang Long","raw_affiliation_strings":["Meta Reality Lab, Burlingame, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Lab, Burlingame, CA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358770","display_name":"Qing Zhang","orcid":"https://orcid.org/0000-0001-5312-2800"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Zhang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067363489","display_name":"Guiqing Li","orcid":"https://orcid.org/0000-0002-4598-1522"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiqing Li","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5162","last_page":"5171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T12290","display_name":"Human Motion and Animation","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9950000047683716,"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/sampling","display_name":"Sampling (signal processing)","score":0.6913667321205139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6367685794830322},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6157787442207336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5212495923042297},{"id":"https://openalex.org/keywords/gumbel-distribution","display_name":"Gumbel distribution","score":0.48905763030052185},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4519311487674713},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.43864381313323975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4155896306037903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36050885915756226},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3252398371696472},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28953802585601807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25703245401382446},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20884358882904053},{"id":"https://openalex.org/keywords/extreme-value-theory","display_name":"Extreme value theory","score":0.13294824957847595}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6913667321205139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367685794830322},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6157787442207336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212495923042297},{"id":"https://openalex.org/C137610916","wikidata":"https://www.wikidata.org/wiki/Q1096862","display_name":"Gumbel distribution","level":3,"score":0.48905763030052185},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4519311487674713},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.43864381313323975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4155896306037903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36050885915756226},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3252398371696472},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28953802585601807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25703245401382446},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20884358882904053},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.13294824957847595},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547956","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1410054889","display_name":null,"funder_award_id":"2019A1515010860, 2021A1515012301","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2623550831","https://openalex.org/W2793483732","https://openalex.org/W2887738788","https://openalex.org/W2902149428","https://openalex.org/W2950568498","https://openalex.org/W2963324990","https://openalex.org/W2963669520","https://openalex.org/W2964203186","https://openalex.org/W2978927732","https://openalex.org/W2983925976","https://openalex.org/W2993797559","https://openalex.org/W2994175816","https://openalex.org/W3034423770","https://openalex.org/W3034696014","https://openalex.org/W3034938233","https://openalex.org/W3035545045","https://openalex.org/W3036644940","https://openalex.org/W3040942941","https://openalex.org/W3101151469","https://openalex.org/W3108262631","https://openalex.org/W3109174848","https://openalex.org/W3109717189","https://openalex.org/W3172615168","https://openalex.org/W3174292795","https://openalex.org/W3177493543","https://openalex.org/W3202590754","https://openalex.org/W3203206590","https://openalex.org/W3204623367","https://openalex.org/W3205071568","https://openalex.org/W3207054996","https://openalex.org/W3207234065","https://openalex.org/W3207857704","https://openalex.org/W4205260486","https://openalex.org/W4214657742","https://openalex.org/W4214722801","https://openalex.org/W4230178929","https://openalex.org/W4234552385","https://openalex.org/W4313056154"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W2565378226","https://openalex.org/W4294294142","https://openalex.org/W2742914308","https://openalex.org/W2330004501","https://openalex.org/W2017089693","https://openalex.org/W2703295919"],"abstract_inverted_index":{"Diverse":[0],"human":[1],"motion":[2],"prediction":[3],"aims":[4],"at":[5,195],"predicting":[6],"multiple":[7,62],"possible":[8],"future":[9],"pose":[10],"sequences":[11],"from":[12,37,100,124,133],"a":[13,69,77,83,91,107,139,153],"sequence":[14],"of":[15,30,64,80,180],"observed":[16],"poses.":[17],"Previous":[18],"approaches":[19],"usually":[20,48],"employ":[21],"deep":[22,108],"generative":[23,109],"networks":[24],"to":[25,129],"model":[26],"the":[27,38,49,65,125,130,134,176,181],"conditional":[28,66],"distribution":[29,67,104],"data,":[31],"and":[32,119,159,178,190],"then":[33],"randomly":[34,122],"sample":[35],"outcomes":[36],"distribution.":[39,136],"While":[40],"different":[41],"results":[42,99],"can":[43,74],"be":[44],"obtained,":[45],"they":[46],"are":[47,54,193],"most":[50],"likely":[51],"ones":[52],"which":[53,72,151],"not":[55],"diverse":[56,98,131],"enough.":[57],"Recent":[58],"work":[59],"explicitly":[60],"learns":[61],"modes":[63,81],"via":[68],"deterministic":[70],"network,":[71],"however":[73],"only":[75],"cover":[76],"fixed":[78],"number":[79],"within":[82],"limited":[84],"range.":[85],"In":[86],"this":[87,147],"paper,":[88],"we":[89],"propose":[90,138],"novel":[92,148],"sampling":[93,96,123,132,149,157,187],"strategy":[94],"for":[95],"very":[97],"an":[101,116,160],"imbalanced":[102],"multimodal":[103],"learned":[105],"by":[106,114],"model.":[110],"Our":[111],"method":[112,158,172],"works":[113],"generating":[115],"auxiliary":[117,126],"space":[118,127],"smartly":[120],"making":[121],"equivalent":[128],"target":[135],"We":[137],"simple":[140],"yet":[141],"effective":[142],"network":[143],"architecture":[144],"that":[145,170],"implements":[146],"strategy,":[150],"incorporates":[152],"Gumbel-Softmax":[154],"coefficient":[155],"matrix":[156],"aggressive":[161],"diversity":[162,177],"promoting":[163],"hinge":[164],"loss":[165],"function.":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"our":[171],"significantly":[173],"improves":[174],"both":[175],"accuracy":[179],"samplings":[182],"compared":[183],"with":[184],"previous":[185],"state-of-the-art":[186],"approaches.":[188],"Code":[189],"pre-trained":[191],"models":[192],"available":[194],"https://github.com/Droliven/diverse_sampling.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}