{"id":"https://openalex.org/W2250680486","doi":"https://doi.org/10.18653/v1/w15-2802","title":"Computational Integration of Human Vision and Natural Language through Bitext Alignment","display_name":"Computational Integration of Human Vision and Natural Language through Bitext Alignment","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250680486","doi":"https://doi.org/10.18653/v1/w15-2802","mag":"2250680486"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2802","pdf_url":"https://www.aclweb.org/anthology/W15-2802.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on Vision and Language","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-2802.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079789157","display_name":"Preethi Vaidyanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Preethi Vaidyanathan","raw_affiliation_strings":["Rochester Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085014772","display_name":"Emily Prud\u2019hommeaux","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Prud'hommeaux","raw_affiliation_strings":["Rochester Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067170834","display_name":"Cecilia Ovesdotter Alm","orcid":"https://orcid.org/0000-0002-8730-0916"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cecilia O. Alm","raw_affiliation_strings":["Rochester Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038705688","display_name":"Jeff B. Pelz","orcid":"https://orcid.org/0000-0002-0649-3876"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff B. Pelz","raw_affiliation_strings":["Rochester Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035006377","display_name":"Anne R. Haake","orcid":"https://orcid.org/0000-0003-0634-0199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anne R. Haake","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079789157"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":0.1999,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60441371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9958999752998352,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9958999752998352,"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":0.9916999936103821,"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":0.9898999929428101,"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":0.8099594712257385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6182873845100403},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5520171523094177},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4692905843257904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45203012228012085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099594712257385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182873845100403},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5520171523094177},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4692905843257904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45203012228012085},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-2802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2802","pdf_url":"https://www.aclweb.org/anthology/W15-2802.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on Vision and Language","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2802","pdf_url":"https://www.aclweb.org/anthology/W15-2802.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on Vision and Language","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250680486.pdf","grobid_xml":"https://content.openalex.org/works/W2250680486.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W152523715","https://openalex.org/W630801560","https://openalex.org/W2123815913","https://openalex.org/W2147018085","https://openalex.org/W2169724380","https://openalex.org/W2251157961"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3204019825","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Multimodal":[0],"integration":[1],"of":[2,39,43],"visual":[3,30],"and":[4,31,53,66],"linguistic":[5,32],"data":[6],"is":[7],"a":[8,19],"longstanding":[9],"but":[10],"crucial":[11],"challenge":[12],"for":[13,63],"modeling":[14],"human":[15],"understanding.":[16],"We":[17,34],"propose":[18],"framework":[20],"that":[21],"uses":[22],"an":[23,36],"unsupervised":[24],"bitext":[25],"alignment":[26],"method":[27],"to":[28],"integrate":[29],"data.":[33],"present":[35],"empirical":[37],"study":[38],"the":[40,44],"various":[41],"parameters":[42],"framework.":[45],"Our":[46],"results":[47],"exceed":[48],"baselines":[49],"using":[50],"both":[51],"exact":[52],"delayed":[54],"temporal":[55],"correspondence.":[56],"The":[57],"resulting":[58],"alignments":[59],"can":[60],"be":[61],"used":[62],"image":[64],"classification":[65],"retrieval.":[67]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}