{"id":"https://openalex.org/W2548652789","doi":"https://doi.org/10.1145/2993148.3011260","title":"Learning to generate images and their descriptions (keynote)","display_name":"Learning to generate images and their descriptions (keynote)","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2548652789","doi":"https://doi.org/10.1145/2993148.3011260","mag":"2548652789"},"language":"en","primary_location":{"id":"doi:10.1145/2993148.3011260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.3011260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","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/A5000111344","display_name":"Richard S. Zemel","orcid":"https://orcid.org/0000-0001-9353-7509"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Richard Zemel","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000111344"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11695504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9674999713897705,"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":0.9465000033378601,"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/computer-science","display_name":"Computer science","score":0.7803298234939575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5855656862258911},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4853724241256714},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4615355432033539},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.41969767212867737},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41071128845214844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35898682475090027},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3351151645183563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803298234939575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855656862258911},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4853724241256714},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4615355432033539},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.41969767212867737},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41071128845214844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35898682475090027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3351151645183563},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2993148.3011260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.3011260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2955859849","https://openalex.org/W2122804826","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229","https://openalex.org/W2140902089","https://openalex.org/W2988746243","https://openalex.org/W2030298461"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,17,38,71],"computer":[3,47],"vision,":[4],"natural":[5,28],"language":[6,51],"processing":[7],"and":[8,50,79],"related":[9],"areas":[10],"has":[11,33],"led":[12,67],"to":[13,53,68],"a":[14],"renewed":[15],"interest":[16],"artificial":[18],"intelligence":[19],"applications":[20],"spanning":[21],"multiple":[22],"domains.":[23],"Specifically,":[24],"the":[25,80],"generation":[26],"of":[27,56,76],"human-like":[29],"captions":[30],"for":[31],"images":[32],"seen":[34],"an":[35],"extraordinary":[36],"increase":[37],"interest.":[39],"I":[40],"will":[41,85],"describe":[42],"approaches":[43,78],"that":[44,82],"combine":[45],"state-of-the-art":[46],"vision":[48],"techniques":[49],"models":[52],"produce":[54],"descriptions":[55],"visual":[57],"content":[58],"with":[59],"surprisingly":[60],"high":[61],"quality.":[62],"Related":[63],"methods":[64],"have":[65],"also":[66],"significant":[69],"progress":[70],"generating":[72],"images.":[73],"The":[74],"limitations":[75],"current":[77],"challenges":[81],"lie":[83],"ahead":[84],"both":[86],"be":[87],"emphasized.":[88]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
