{"id":"https://openalex.org/W4308393099","doi":"https://doi.org/10.1145/3536221.3556596","title":"Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments","display_name":"Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4308393099","doi":"https://doi.org/10.1145/3536221.3556596"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3556596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3536221.3556596","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103253154","display_name":"Abhinav Joshi","orcid":"https://orcid.org/0000-0001-6756-1126"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhinav Joshi","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kanpur, India"],"raw_orcid":"https://orcid.org/0000-0001-6756-1126","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062962997","display_name":"Naman Gupta","orcid":"https://orcid.org/0000-0001-9908-4272"},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Naman Gupta","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology, India"],"raw_orcid":"https://orcid.org/0000-0001-9908-4272","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology, India","institution_ids":["https://openalex.org/I64295750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042272378","display_name":"Jinang Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jinang Shah","raw_affiliation_strings":["Indian Institute of Technology Kanpur, India"],"raw_orcid":"https://orcid.org/0000-0002-3081-5345","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063234434","display_name":"Binod Bhattarai","orcid":"https://orcid.org/0000-0001-7171-6469"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Binod Bhattarai","raw_affiliation_strings":["University College London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7171-6469","affiliations":[{"raw_affiliation_string":"University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076043215","display_name":"Ashutosh Modi","orcid":"https://orcid.org/0000-0002-0962-8350"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashutosh Modi","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kanpur, India"],"raw_orcid":"https://orcid.org/0000-0002-0962-8350","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077630267","display_name":"Danail Stoyanov","orcid":"https://orcid.org/0000-0002-0980-3227"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danail Stoyanov","raw_affiliation_strings":["University College London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0980-3227","affiliations":[{"raw_affiliation_string":"University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103253154"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.3048,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5541995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9961000084877014,"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":0.9861999750137329,"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":0.8057320713996887},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.656922459602356},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6416515111923218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6322586536407471},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6031169295310974},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5394225120544434},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5291640758514404},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5118054747581482},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49768760800361633},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4443493187427521},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44407525658607483},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.44032731652259827},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43831273913383484},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12479585409164429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057320713996887},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.656922459602356},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6416515111923218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322586536407471},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6031169295310974},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5394225120544434},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5291640758514404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5118054747581482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49768760800361633},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4443493187427521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44407525658607483},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.44032731652259827},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43831273913383484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12479585409164429},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3536221.3556596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10162124","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10162124/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  ICMI '22: Proceedings of the 2022 International Conference on Multimodal Interaction.  (pp. pp. 83-93).  ACM: New York, NY, United States. (2022)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.1145/3536221.3556596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1737217355","display_name":null,"funder_award_id":"EP/P012841/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2567867310","display_name":null,"funder_award_id":"GA863146","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2753738274","https://openalex.org/W2796426482","https://openalex.org/W2799191197","https://openalex.org/W2892644985","https://openalex.org/W2903283814","https://openalex.org/W2962811204","https://openalex.org/W2963207848","https://openalex.org/W2970546341","https://openalex.org/W2982601397","https://openalex.org/W2984624776","https://openalex.org/W3097710762","https://openalex.org/W3099686304","https://openalex.org/W3101310341","https://openalex.org/W3109623365","https://openalex.org/W3136640957","https://openalex.org/W3140817806","https://openalex.org/W3157083125","https://openalex.org/W3162791757","https://openalex.org/W3184201478","https://openalex.org/W3184212829"],"related_works":["https://openalex.org/W2248852396","https://openalex.org/W73545470","https://openalex.org/W199123384","https://openalex.org/W4239305747","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209"],"abstract_inverted_index":{"A":[0],"real-world":[1],"application":[2],"or":[3],"setting":[4],"involves":[5,45],"interaction":[6],"between":[7],"different":[8,66],"modalities":[9],"(e.g.,":[10],"video,":[11],"speech,":[12],"text).":[13],"In":[14,71,96,119],"order":[15],"to":[16,89,131,197],"process":[17],"the":[18,62,83,86,92,113,120,133,143,153,191],"multimodal":[19,94,105,168,173],"information":[20,52,136],"automatically":[21],"and":[22,48,56,141,172,187],"use":[23],"it":[24],"for":[25,104,128],"an":[26,36],"end":[27],"application,":[28],"Multimodal":[29],"Representation":[30],"Learning":[31],"(MRL)":[32],"has":[33],"emerged":[34],"as":[35],"active":[37],"area":[38],"of":[39,51,77,85,116,135,193],"research":[40],"in":[41,60,91,108],"recent":[42],"times.":[43],"MRL":[44],"learning":[46,107],"reliable":[47],"robust":[49],"representations":[50],"from":[53,65,138,145,164],"heterogeneous":[54],"sources":[55,67],"fusing":[57],"them.":[58],"However,":[59],"practice,":[61],"data":[63,87],"acquired":[64],"are":[68],"typically":[69],"noisy.":[70],"some":[72],"extreme":[73],"cases,":[74],"a":[75,101,109,125],"noise":[76],"large":[78],"magnitude":[79],"can":[80],"completely":[81],"alter":[82],"semantics":[84],"leading":[88],"inconsistencies":[90],"parallel":[93],"data.":[95],"this":[97],"paper,":[98],"we":[99,123],"propose":[100],"novel":[102],"method":[103,159,195],"representation":[106],"noisy":[110],"environment":[111],"via":[112],"generalized":[114],"product":[115],"experts":[117],"technique.":[118],"proposed":[121],"method,":[122],"train":[124],"separate":[126],"network":[127],"each":[129,146],"modality":[130,147],"assess":[132],"credibility":[134],"coming":[137],"that":[139],"modality,":[140],"subsequently,":[142],"contribution":[144],"is":[148],"dynamically":[149],"varied":[150],"while":[151],"estimating":[152],"joint":[154],"distribution.":[155],"We":[156,177],"evaluate":[157],"our":[158,194],"on":[160,181],"two":[161,165],"challenging":[162],"benchmarks":[163],"diverse":[166],"domains:":[167],"3D":[169],"hand-pose":[170],"estimation":[171],"surgical":[174],"video":[175],"segmentation.":[176],"attain":[178],"state-of-the-art":[179],"performance":[180],"both":[182],"benchmarks.":[183],"Our":[184],"extensive":[185],"quantitative":[186],"qualitative":[188],"evaluations":[189],"show":[190],"advantages":[192],"compared":[196],"previous":[198],"approaches.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}