{"id":"https://openalex.org/W3102363545","doi":"https://doi.org/10.1109/icpr48806.2021.9412679","title":"Mutual Information based Method for Unsupervised Disentanglement of Video Representation","display_name":"Mutual Information based Method for Unsupervised Disentanglement of Video Representation","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3102363545","doi":"https://doi.org/10.1109/icpr48806.2021.9412679","mag":"3102363545"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.08614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080334347","display_name":"P Aditya Sreekar","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P Aditya Sreekar","raw_affiliation_strings":["Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","International Institute of Information Technology, Hyderabad;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad;","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052201567","display_name":"Ujjwal Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ujjwal Tiwari","raw_affiliation_strings":["Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","International Institute of Information Technology, Hyderabad;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad;","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000176044","display_name":"Anoop Namboodiri","orcid":"https://orcid.org/0000-0002-4638-0833"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anoop Namboodiri","raw_affiliation_strings":["Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","International Institute of Information Technology, Hyderabad;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology, International Institute of Information Technology, Hyderabad","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad;","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.0941,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32686649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"6396","last_page":"6403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9851999878883362,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9830999970436096,"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":0.798558235168457},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.7620441913604736},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6832215785980225},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6288208365440369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6249089241027832},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6051449775695801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.59797203540802},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5287213921546936},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46816253662109375},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45175281167030334},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.4361407160758972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38120540976524353},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36168837547302246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3465145230293274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798558235168457},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.7620441913604736},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6832215785980225},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6288208365440369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6249089241027832},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6051449775695801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.59797203540802},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5287213921546936},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46816253662109375},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45175281167030334},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.4361407160758972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38120540976524353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36168837547302246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3465145230293274},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.08614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08614","pdf_url":"https://arxiv.org/pdf/2011.08614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3102363545","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.08614","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.08614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.08614","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.08614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08614","pdf_url":"https://arxiv.org/pdf/2011.08614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3102363545.pdf","grobid_xml":"https://content.openalex.org/works/W3102363545.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1522301498","https://openalex.org/W1527042480","https://openalex.org/W1568514080","https://openalex.org/W1661915592","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1984383922","https://openalex.org/W2082290707","https://openalex.org/W2092939357","https://openalex.org/W2099471712","https://openalex.org/W2116435618","https://openalex.org/W2136144249","https://openalex.org/W2163922914","https://openalex.org/W2166944917","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2528489519","https://openalex.org/W2559823555","https://openalex.org/W2559927751","https://openalex.org/W2615413256","https://openalex.org/W2738136547","https://openalex.org/W2753738274","https://openalex.org/W2765363933","https://openalex.org/W2783047733","https://openalex.org/W2785519580","https://openalex.org/W2788033868","https://openalex.org/W2793111190","https://openalex.org/W2796303840","https://openalex.org/W2808697642","https://openalex.org/W2903538854","https://openalex.org/W2944503153","https://openalex.org/W2946006146","https://openalex.org/W2948215242","https://openalex.org/W2949099979","https://openalex.org/W2951004968","https://openalex.org/W2962785568","https://openalex.org/W2963045453","https://openalex.org/W2963092440","https://openalex.org/W2963226019","https://openalex.org/W2963305465","https://openalex.org/W2963402657","https://openalex.org/W2963610939","https://openalex.org/W2963618559","https://openalex.org/W2963657860","https://openalex.org/W2963800509","https://openalex.org/W2964127395","https://openalex.org/W2968967434","https://openalex.org/W4211083646","https://openalex.org/W4232613155","https://openalex.org/W6677326919","https://openalex.org/W6712884540","https://openalex.org/W6717434760","https://openalex.org/W6718140377","https://openalex.org/W6726983635","https://openalex.org/W6738467200","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6748391871","https://openalex.org/W6752365561","https://openalex.org/W6762796984"],"related_works":["https://openalex.org/W3157480928","https://openalex.org/W3172249638","https://openalex.org/W3209858843","https://openalex.org/W3206718933","https://openalex.org/W2994515381","https://openalex.org/W2584471052","https://openalex.org/W2588950296","https://openalex.org/W1568514080","https://openalex.org/W3022026031","https://openalex.org/W2798788386","https://openalex.org/W2964931564","https://openalex.org/W2794977364","https://openalex.org/W2991327061","https://openalex.org/W3016475064","https://openalex.org/W2950503707","https://openalex.org/W2963631366","https://openalex.org/W2990330482","https://openalex.org/W3082582306","https://openalex.org/W2786698010","https://openalex.org/W3201625964"],"abstract_inverted_index":{"Video":[0,24],"Prediction":[1],"is":[2,47,119],"a":[3,13,21,60,105,143],"challenging":[4],"but":[5],"interesting":[6],"task":[7,70],"of":[8,39,52,71,100,156,169],"predicting":[9,72],"future":[10,44,138],"frames":[11,17,76,170],"from":[12],"given":[14],"set":[15],"context":[16],"that":[18,67],"belong":[19],"to":[20,110,121,136,151],"video":[22,75,79,101,113],"sequence.":[23],"prediction":[25],"models":[26],"have":[27],"prospective":[28],"applications":[29],"in":[30,43,95],"maneuver":[31],"planning,":[32],"healthcare,":[33],"autonomous":[34],"navigation":[35],"and":[36,83,129,160,183],"simulation.":[37],"One":[38],"the":[40,48,69,92,96,130,154,166],"major":[41],"challenges":[42],"frame":[45],"generation":[46],"high":[49,73],"dimensional":[50,74,85,125],"nature":[51],"visual":[53,167],"data.":[54],"To":[55],"handle":[56],"this,":[57],"we":[58],"propose":[59,142],"Mutual":[61],"Information":[62],"Predictive":[63],"Auto-Encoder":[64],"(MIPAE)":[65],"framework":[66],"reduces":[68],"by":[77,103,172],"factorising":[78],"representations":[80,133],"into":[81],"content":[82],"low":[84,124],"pose":[86,126,132],"latent":[87,97],"variables.":[88],"Our":[89],"approach":[90],"leverages":[91],"temporal":[93],"structure":[94],"generative":[98],"factors":[99],"sequences":[102],"applying":[104],"novel":[106],"mutual":[107,147],"information":[108,148],"loss":[109],"learn":[111],"disentangled":[112],"representations.":[114,127],"A":[115],"standard":[116],"LSTM":[117],"network":[118],"used":[120],"predict":[122],"these":[123],"Content":[128],"predicted":[131,171],"are":[134],"decoded":[135],"generate":[137],"frames.":[139],"We":[140,174],"also":[141,175],"metric":[144],"based":[145],"on":[146,158,180],"gap":[149],"(MIG)":[150],"quantitatively":[152,179],"access":[153],"effectiveness":[155],"disentanglement":[157],"DSprites":[159],"MPI3D-real":[161],"datasets.":[162],"MIG":[163],"scores":[164],"corroborate":[165],"superiority":[168],"MIPAE.":[173],"compare":[176],"our":[177],"method":[178],"LPIPS,":[181],"SSIM":[182],"PSNR":[184],"evaluation":[185],"metrics.":[186]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
