{"id":"https://openalex.org/W2995368430","doi":null,"title":"Vector Spaces for Multiple Modal Embeddings","display_name":"Vector Spaces for Multiple Modal Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2995368430","mag":"2995368430"},"language":"en","primary_location":{"id":"pmh:oai:scholarworks.rit.edu:theses-11431","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.rit.edu/theses/10283","pdf_url":"https://scholarworks.rit.edu/theses/10283","source":{"id":"https://openalex.org/S4306402456","display_name":"RIT Scholar Works (Rochester Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155173764","host_organization_name":"Rochester Institute of Technology","host_organization_lineage":["https://openalex.org/I155173764"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses","raw_type":"text"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.rit.edu/theses/10283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077348601","display_name":"Sabarish Gopalakrishnan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sabarish Gopalakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5077348601"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9657999873161316,"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":0.9657999873161316,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.01889999955892563,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.004100000020116568,"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/multimodal-embeddings","display_name":"multimodal embeddings","score":0.7160000205039978},{"id":"https://openalex.org/keywords/vector-spaces","display_name":"vector spaces","score":0.7599999904632568},{"id":"https://openalex.org/keywords/cross-modal-retrieval","display_name":"cross-modal retrieval","score":0.949999988079071},{"id":"https://openalex.org/keywords/modality-transfer","display_name":"modality transfer","score":0.5989999771118164},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.5690000057220459},{"id":"https://openalex.org/keywords/audio-text-retrieval","display_name":"audio-text retrieval","score":0.8029999732971191},{"id":"https://openalex.org/keywords/text-video-retrieval","display_name":"video-text retrieval","score":0.843999981880188}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5552154779434204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4298037588596344},{"id":"https://openalex.org/C114092440","wikidata":"https://www.wikidata.org/wiki/Q840226","display_name":"Normal modal logic","level":4,"score":0.42502155900001526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4016351103782654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.292643278837204},{"id":"https://openalex.org/C203659156","wikidata":"https://www.wikidata.org/wiki/Q6934805","display_name":"Multimodal logic","level":3,"score":0.11046159267425537},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:scholarworks.rit.edu:theses-11431","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.rit.edu/theses/10283","pdf_url":"https://scholarworks.rit.edu/theses/10283","source":{"id":"https://openalex.org/S4306402456","display_name":"RIT Scholar Works (Rochester Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155173764","host_organization_name":"Rochester Institute of Technology","host_organization_lineage":["https://openalex.org/I155173764"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses","raw_type":"text"},{"id":"pmh:oai:repository.rit.edu:theses-11431","doi":null,"is_oa":false,"landing_page_url":"https://repository.rit.edu/theses/10283","pdf_url":null,"source":{"id":"https://openalex.org/S4306402456","display_name":"RIT Scholar Works (Rochester Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155173764","host_organization_name":"Rochester Institute of Technology","host_organization_lineage":["https://openalex.org/I155173764"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses","raw_type":"text"},{"id":"mag:2995368430","doi":null,"is_oa":false,"landing_page_url":"https://scholarworks.rit.edu/cgi/viewcontent.cgi?article=11431&context=theses","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:scholarworks.rit.edu:theses-11431","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.rit.edu/theses/10283","pdf_url":"https://scholarworks.rit.edu/theses/10283","source":{"id":"https://openalex.org/S4306402456","display_name":"RIT Scholar Works (Rochester Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155173764","host_organization_name":"Rochester Institute of Technology","host_organization_lineage":["https://openalex.org/I155173764"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2995368430.pdf","grobid_xml":"https://content.openalex.org/works/W2995368430.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1903029394","https://openalex.org/W1904365287","https://openalex.org/W1947481528","https://openalex.org/W1964073652","https://openalex.org/W1974101426","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2016053056","https://openalex.org/W2052727801","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2100235303","https://openalex.org/W2108598243","https://openalex.org/W2119775030","https://openalex.org/W2136848157","https://openalex.org/W2156303437","https://openalex.org/W2163605009","https://openalex.org/W2164587673","https://openalex.org/W2172888184","https://openalex.org/W2342543219","https://openalex.org/W2398118205","https://openalex.org/W2476548250","https://openalex.org/W2508827254","https://openalex.org/W2606473278","https://openalex.org/W2606965845","https://openalex.org/W2612131472","https://openalex.org/W2736876693","https://openalex.org/W2794376802","https://openalex.org/W2795389793","https://openalex.org/W2795832645","https://openalex.org/W2798280084","https://openalex.org/W2807722546","https://openalex.org/W2890769421","https://openalex.org/W2952122856","https://openalex.org/W2963446712","https://openalex.org/W2963526065","https://openalex.org/W2963766818","https://openalex.org/W2964199361","https://openalex.org/W3105204788"],"related_works":["https://openalex.org/W3081070642","https://openalex.org/W3080208472","https://openalex.org/W3013561077","https://openalex.org/W2891150491","https://openalex.org/W3026614632","https://openalex.org/W2922793760","https://openalex.org/W2145056192","https://openalex.org/W4407704939","https://openalex.org/W3206272031","https://openalex.org/W2155548388"],"abstract_inverted_index":{"Deep":[0,20],"learning":[1,21,72],"has":[2],"enabled":[3],"great":[4],"advances":[5],"in":[6,18,27,65,152],"the":[7,93,101,124,206,212,222],"field":[8],"of":[9,43,83,95,142,154,165,176,214],"natural":[10],"language":[11],"processing,":[12],"computer":[13],"vision":[14],"and":[15,33,53,61,88,135,157,188,200,208],"pattern":[16],"recognition":[17],"general.":[19],"frameworks":[22],"have":[23],"been":[24],"very":[25],"successful":[26],"performing":[28,232],"classification,":[29],"object":[30,45],"detection,":[31],"segmentation":[32],"translation.":[34],"Before":[35],"objects":[36,131,137],"can":[37,55,115,149,170,194,210],"be":[38,48,56,150],"processed,":[39],"a":[40,59,70,104,146,163,166,177,182,215],"vector":[41,81,112,147],"representation":[42,82],"that":[44,114,118,193],"needs":[46],"to":[47,69,78,100,120,220],"created.":[49],"For":[50,160],"example,":[51,161],"sentences":[52,172],"images":[54],"encoded":[57],"with":[58],"sent2vec":[60],"image2vec":[62],"function":[63],"respectively":[64],"preparation":[66],"for":[67],"input":[68],"machine":[71],"framework.":[73],"Neural":[74],"networks":[75],"are":[76,132,138],"able":[77],"learn":[79],"efficient":[80],"images,":[84,196],"text,":[85,197],"audio,":[86],"videos":[87,199],"3D":[89,201],"point":[90,202],"clouds.":[91],"However,":[92],"transfer":[94],"knowledge":[96],"from":[97],"one":[98,169],"modality":[99,217],"other":[102],"is":[103,229],"challenging":[105],"task.":[106],"In":[107,127],"this":[108],"work,":[109],"we":[110],"develop":[111],"spaces":[113],"handle":[116,195,211],"data":[117],"belongs":[119],"multiple":[121,237],"modalities":[122],"at":[123],"same":[125],"time.":[126],"these":[128],"spaces,":[129],"similar":[130],"tightly":[133],"clustered":[134],"dissimilar":[136],"far":[139],"away":[140],"irrespective":[141],"their":[143],"modality.":[144],"Such":[145],"space":[148],"used":[151],"retrieval":[153,235],"objects,":[155],"searching":[156],"generation":[158],"tasks.":[159],"given":[162],"picture":[164],"person":[167,178],"surfing,":[168],"retrieve":[171],"or":[173,225],"audio":[174],"bites":[175],"surfing.":[179],"We":[180],"build":[181],"Multi-stage":[183],"Common":[184],"Vector":[185,190],"Space":[186,191],"(M-CVS)":[187],"Reference":[189],"(RVS)":[192],"audios,":[198],"cloud":[203],"data.":[204],"Both,":[205],"M-CVS":[207],"RVS":[209],"addition":[213],"new":[216],"without":[218],"having":[219],"change":[221],"existing":[223],"transforms":[224],"architecture.":[226],"Our":[227],"model":[228],"evaluated":[230],"by":[231],"cross":[233],"modal":[234],"on":[236],"benchmark":[238],"datasets.":[239]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-12-26T00:00:00"}