{"id":"https://openalex.org/W2530301083","doi":"https://doi.org/10.1145/2983563.2986050","title":"Jointly Representing Images and Text","display_name":"Jointly Representing Images and Text","publication_year":2016,"publication_date":"2016-10-11","ids":{"openalex":"https://openalex.org/W2530301083","doi":"https://doi.org/10.1145/2983563.2986050","mag":"2530301083"},"language":"en","primary_location":{"id":"doi:10.1145/2983563.2986050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983563.2986050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM workshop on Vision and Language Integration Meets Multimedia Fusion","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/10085282-2909-4390-a66e-b6c34de142ac","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Frank Keller","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054936589"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.8448781967163086},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8263818621635437},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.7596383094787598},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6542543172836304},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5913697481155396},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5102221965789795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39257127046585083},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.319313108921051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448781967163086},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8263818621635437},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.7596383094787598},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6542543172836304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5913697481155396},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5102221965789795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39257127046585083},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.319313108921051}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2983563.2986050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983563.2986050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM workshop on Vision and Language Integration Meets Multimedia Fusion","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/10085282-2909-4390-a66e-b6c34de142ac","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/10085282-2909-4390-a66e-b6c34de142ac","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Keller, F 2016, Jointly Representing Images and Text: Dependency Graphs, Word Senses, and Multimodal Embeddings. in Proceedings of the 2016 ACM Workshop on Vision and Language Integration Meets Multimedia Fusion. iV38;L-MM '16, New York, NY, USA, pp. 35-36, 2016 ACM Workshop on Vision and Language Integration Meets Multimedia Fusion, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2983563.2986050","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/10085282-2909-4390-a66e-b6c34de142ac","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?doid=2983563.2986050","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/10085282-2909-4390-a66e-b6c34de142ac","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/10085282-2909-4390-a66e-b6c34de142ac","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Keller, F 2016, Jointly Representing Images and Text: Dependency Graphs, Word Senses, and Multimodal Embeddings. in Proceedings of the 2016 ACM Workshop on Vision and Language Integration Meets Multimedia Fusion. iV38;L-MM '16, New York, NY, USA, pp. 35-36, 2016 ACM Workshop on Vision and Language Integration Meets Multimedia Fusion, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2983563.2986050","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W81000870","https://openalex.org/W1734113335","https://openalex.org/W1999993003","https://openalex.org/W2077069816","https://openalex.org/W2100751297","https://openalex.org/W2108598243","https://openalex.org/W2143449221","https://openalex.org/W2163605009","https://openalex.org/W2226480163","https://openalex.org/W2250379249","https://openalex.org/W2618530766","https://openalex.org/W2771472444","https://openalex.org/W2963852185","https://openalex.org/W4205509257","https://openalex.org/W6637665129"],"related_works":["https://openalex.org/W2944823289","https://openalex.org/W3037018281","https://openalex.org/W2003209439","https://openalex.org/W4321854979","https://openalex.org/W2358319515","https://openalex.org/W2972592048","https://openalex.org/W4312214821","https://openalex.org/W2497626292","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"The":[0],"amount":[1],"of":[2,25,31,70],"image":[3],"data":[4,27],"available":[5],"on":[6,12,68,74],"the":[7,75],"web":[8],"is":[9],"growing":[10],"rapidly:":[11],"Facebook":[13],"alone,":[14],"350":[15],"million":[16],"new":[17,29],"images":[18],"are":[19],"uploaded":[20],"every":[21],"day.":[22],"Making":[23],"sense":[24],"this":[26,46],"requires":[28],"ways":[30],"efficiently":[32],"indexing,":[33],"annotating,":[34],"and":[35,53],"querying":[36],"such":[37],"enormous":[38],"collections.":[39],"Research":[40],"in":[41,56],"computer":[42],"vision":[43],"has":[44],"tackled":[45],"problem":[47],"by":[48],"developing":[49],"algorithms":[50,60],"for":[51],"localizing":[52],"labeling":[54],"objects":[55],"images.":[57],"Object":[58],"classification":[59],"have":[61],"been":[62],"recently":[63],"scaled":[64],"up":[65],"to":[66],"work":[67],"thousands":[69],"object":[71],"classes":[72],"based":[73],"ImageNet":[76],"database.":[77]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}