{"id":"https://openalex.org/W2527238922","doi":"https://doi.org/10.1145/2964284.2967212","title":"Joint Image-Text Representation by Gaussian Visual-Semantic Embedding","display_name":"Joint Image-Text Representation by Gaussian Visual-Semantic Embedding","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2527238922","doi":"https://doi.org/10.1145/2964284.2967212","mag":"2527238922"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","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/A5083293468","display_name":"Zhou Ren","orcid":"https://orcid.org/0000-0002-1402-966X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhou Ren","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109787260","display_name":"Hailin Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hailin Jin","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564904","display_name":"Zhe Lin","orcid":"https://orcid.org/0000-0003-1154-9907"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Lin","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Fang","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Yuille","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083293468"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":5.4177,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97363889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"211"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9991999864578247,"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":0.771236777305603},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.737794041633606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.587468683719635},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.4977617561817169},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4800516366958618},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47540292143821716},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.44800102710723877},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.43010714650154114},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42817550897598267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3688491880893707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3684474229812622},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3303954601287842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771236777305603},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.737794041633606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587468683719635},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.4977617561817169},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4800516366958618},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47540292143821716},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.44800102710723877},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.43010714650154114},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42817550897598267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3688491880893707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3684474229812622},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3303954601287842},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W93016980","https://openalex.org/W1514027499","https://openalex.org/W1527575280","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2082453965","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2123024445","https://openalex.org/W2134670479","https://openalex.org/W2153579005","https://openalex.org/W2155893237","https://openalex.org/W2202987080","https://openalex.org/W2250539671","https://openalex.org/W2255924030","https://openalex.org/W2950133940","https://openalex.org/W2950700180","https://openalex.org/W2962706528","https://openalex.org/W2962796133","https://openalex.org/W2963346784","https://openalex.org/W6678470764","https://openalex.org/W6678984984","https://openalex.org/W6691979365"],"related_works":["https://openalex.org/W3140002740","https://openalex.org/W2947722169","https://openalex.org/W3090743472","https://openalex.org/W3026491381","https://openalex.org/W4226361842","https://openalex.org/W3048163579","https://openalex.org/W2255924030","https://openalex.org/W2081414063","https://openalex.org/W4210441873","https://openalex.org/W4205247775"],"abstract_inverted_index":{"How":[0],"to":[1,23,46,62,72,117],"jointly":[2],"represent":[3],"images":[4,36],"and":[5,21,50,88,133,157],"texts":[6],"is":[7,29,44],"important":[8],"for":[9],"tasks":[10],"involving":[11],"both":[12],"modalities.":[13],"Visual-semantic":[14],"embedding":[15],"models":[16],"have":[17,144],"been":[18],"recently":[19],"proposed":[20],"shown":[22],"be":[24],"effective.":[25],"The":[26],"key":[27],"idea":[28],"that":[30],"by":[31],"learning":[32],"a":[33,38,48,63,73,105],"mapping":[34],"from":[35],"into":[37],"semantic":[39,68,125],"text":[40,60,86,119],"space,":[41],"the":[42,67,114,138,146],"algorithm":[43],"able":[45],"learn":[47],"compact":[49],"effective":[51],"joint":[52],"representation.":[53],"However,":[54],"existing":[55,152],"approaches":[56],"simply":[57],"map":[58],"each":[59,85],"concept":[61],"single":[64],"point":[65],"in":[66,124,128],"space.":[69,126],"Mapping":[70],"instead":[71],"density":[74],"distribution":[75],"provides":[76],"many":[77],"interesting":[78],"advantages,":[79],"including":[80],"better":[81,90,158],"capturing":[82],"uncertainty":[83],"about":[84],"concept,":[87],"enabling":[89],"geometric":[91],"interpretation":[92],"of":[93,148],"concepts":[94,120],"such":[95],"as":[96,121],"inclusion,":[97],"intersection,":[98],"etc.":[99],"In":[100],"this":[101],"work,":[102],"we":[103],"present":[104],"novel":[106],"Gaussian":[107,122],"Visual-Semantic":[108],"Embedding":[109],"(GVSE)":[110],"model,":[111],"which":[112],"leverages":[113],"visual":[115],"information":[116],"model":[118],"distributions":[123],"Experiments":[127],"two":[129],"tasks,":[130],"image":[131,135],"classification":[132],"text-based":[134],"retrieval":[136],"on":[137],"large":[139],"scale":[140],"MIT":[141],"Places205":[142],"dataset,":[143],"demonstrated":[145],"superiority":[147],"our":[149],"method":[150],"over":[151],"approaches,":[153],"with":[154],"higher":[155],"accuracy":[156],"robustness.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}