{"id":"https://openalex.org/W2940145719","doi":"https://doi.org/10.1109/icassp.2019.8683370","title":"Learning Disentangled Representation in Latent Stochastic Models: A Case Study with Image Captioning","display_name":"Learning Disentangled Representation in Latent Stochastic Models: A Case Study with Image Captioning","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940145719","doi":"https://doi.org/10.1109/icassp.2019.8683370","mag":"2940145719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5081625117","display_name":"Nidhi Vyas","orcid":"https://orcid.org/0009-0008-0537-8420"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhi Vyas","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027882620","display_name":"SaiKrishna Rallabandi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"SaiKrishna Rallabandi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088278491","display_name":"Lalitesh Morishetti","orcid":"https://orcid.org/0009-0004-9085-9587"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lalitesh Morishetti","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard Hovy","orcid":"https://orcid.org/0000-0002-3270-7903"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.2032,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52281602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4010","last_page":"4014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9957000017166138,"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/closed-captioning","display_name":"Closed captioning","score":0.802696704864502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501393556594849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6947048902511597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5892956256866455},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5784205198287964},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5736882090568542},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5398011207580566},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5088129639625549},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5038673281669617},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48933476209640503},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44902172684669495},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.4295508861541748},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24218252301216125}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.802696704864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501393556594849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6947048902511597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892956256866455},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5784205198287964},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5736882090568542},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5398011207580566},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5088129639625549},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5038673281669617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48933476209640503},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44902172684669495},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.4295508861541748},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24218252301216125},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":71,"referenced_works":["https://openalex.org/W60493759","https://openalex.org/W592244745","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2171361956","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2548228487","https://openalex.org/W2560512785","https://openalex.org/W2560730294","https://openalex.org/W2587284713","https://openalex.org/W2607059968","https://openalex.org/W2608109911","https://openalex.org/W2611009517","https://openalex.org/W2618127004","https://openalex.org/W2619383789","https://openalex.org/W2751076446","https://openalex.org/W2753738274","https://openalex.org/W2772114856","https://openalex.org/W2777449390","https://openalex.org/W2796302026","https://openalex.org/W2796704765","https://openalex.org/W2890952074","https://openalex.org/W2893554781","https://openalex.org/W2906586812","https://openalex.org/W2952165242","https://openalex.org/W2952782394","https://openalex.org/W2953046278","https://openalex.org/W2962717182","https://openalex.org/W2962790223","https://openalex.org/W2962968835","https://openalex.org/W2963178695","https://openalex.org/W2963223306","https://openalex.org/W2963594498","https://openalex.org/W2963611966","https://openalex.org/W2963644680","https://openalex.org/W2963645026","https://openalex.org/W2963891243","https://openalex.org/W2964042872","https://openalex.org/W2964185501","https://openalex.org/W2980216782","https://openalex.org/W3036996956","https://openalex.org/W3104379732","https://openalex.org/W4297744728","https://openalex.org/W4299408792","https://openalex.org/W6602483677","https://openalex.org/W6617744952","https://openalex.org/W6639432524","https://openalex.org/W6640963894","https://openalex.org/W6688384872","https://openalex.org/W6718991148","https://openalex.org/W6730091202","https://openalex.org/W6730998768","https://openalex.org/W6733471323","https://openalex.org/W6736412300","https://openalex.org/W6736692598","https://openalex.org/W6738199216","https://openalex.org/W6741977017","https://openalex.org/W6743386221","https://openalex.org/W6746537959","https://openalex.org/W6746806458","https://openalex.org/W6747385936","https://openalex.org/W6748976544","https://openalex.org/W6750039850","https://openalex.org/W6750852989","https://openalex.org/W6755038706","https://openalex.org/W6756559799","https://openalex.org/W6757733994"],"related_works":["https://openalex.org/W2242083226","https://openalex.org/W2884410131","https://openalex.org/W1603253275","https://openalex.org/W120501756","https://openalex.org/W111011176","https://openalex.org/W2138996412","https://openalex.org/W2763292376","https://openalex.org/W2097596242","https://openalex.org/W3041425257","https://openalex.org/W2906932471"],"abstract_inverted_index":{"Multimodal":[0],"tasks":[1],"require":[2],"learning":[3,53],"joint":[4,66],"representation":[5,52,70],"across":[6],"modalities.":[7],"In":[8],"this":[9],"paper,":[10],"we":[11],"present":[12,57],"an":[13,58],"approach":[14,59,81,103],"to":[15,60,108],"employ":[16],"latent":[17,31,41,89],"stochastic":[18,30,90],"models":[19,28,63],"for":[20],"a":[21,83,95],"multimodal":[22],"task":[23],"image":[24],"captioning.":[25],"Encoder":[26],"Decoder":[27],"with":[29,36],"variables":[32],"are":[33],"often":[34],"faced":[35],"optimization":[37],"issues":[38],"such":[39,62],"as":[40],"collapse":[42],"preventing":[43],"them":[44],"from":[45],"realizing":[46],"their":[47],"full":[48],"potential":[49,107],"of":[50,79,85],"rich":[51],"and":[54,68,98,112],"disentanglement.":[55],"We":[56,75,92],"train":[61],"by":[64],"incorporating":[65],"continuous":[67],"discrete":[69],"in":[71,118],"the":[72,77,101,106,119],"prior":[73],"distribution.":[74],"evaluate":[76],"performance":[78],"proposed":[80,102],"on":[82],"multitude":[84],"metrics":[86],"against":[87],"vanilla":[88],"models.":[91],"also":[93],"perform":[94],"qualitative":[96],"assessment":[97],"observe":[99],"that":[100],"indeed":[104],"has":[105],"learn":[109],"composite":[110],"information":[111],"explain":[113],"novel":[114],"combinations":[115],"not":[116],"seen":[117],"training":[120],"data.":[121]},"counts_by_year":[{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}