{"id":"https://openalex.org/W2250695743","doi":"https://doi.org/10.18653/v1/w15-4722","title":"Generating Image Descriptions with Gold Standard Visual Inputs: Motivation, Evaluation and Baselines","display_name":"Generating Image Descriptions with Gold Standard Visual Inputs: Motivation, Evaluation and Baselines","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250695743","doi":"https://doi.org/10.18653/v1/w15-4722","mag":"2250695743"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4722","pdf_url":"https://www.aclweb.org/anthology/W15-4722.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 15th European Workshop on Natural Language Generation (ENLG)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-4722.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031749307","display_name":"Josiah Wang","orcid":"https://orcid.org/0000-0003-0048-3893"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josiah Wang","raw_affiliation_strings":["Department of Computer Science University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040587162","display_name":"Robert Gaizauskas","orcid":"https://orcid.org/0000-0002-3356-5126"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert Gaizauskas","raw_affiliation_strings":["Department of Computer Science University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9975000023841858,"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":0.7956184148788452},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7651623487472534},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6315312385559082},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6274807453155518},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5609367489814758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502830743789673},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5487308502197266},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5461947321891785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5452899932861328},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5202373266220093},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4279312789440155},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.41627538204193115},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38371822237968445},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32343417406082153},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2752446234226227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956184148788452},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7651623487472534},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6315312385559082},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6274807453155518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5609367489814758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502830743789673},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5487308502197266},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5461947321891785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5452899932861328},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5202373266220093},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4279312789440155},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.41627538204193115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38371822237968445},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32343417406082153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2752446234226227},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w15-4722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4722","pdf_url":"https://www.aclweb.org/anthology/W15-4722.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 15th European Workshop on Natural Language Generation (ENLG)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:99026","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.9020","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.9020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://josiahwang.com/publications/enlg15.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4722","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4722","pdf_url":"https://www.aclweb.org/anthology/W15-4722.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 15th European Workshop on Natural Language Generation (ENLG)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3092958677","display_name":"VisualSense","funder_award_id":"EP/K019082/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5220784469","display_name":"Annotation de donn\u00e9es visuelles avec des descriptions s\u00e9mantiques","funder_award_id":"ANR-12-CHRI-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250695743.pdf","grobid_xml":"https://content.openalex.org/works/W2250695743.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W179875071","https://openalex.org/W1250889301","https://openalex.org/W1645937837","https://openalex.org/W1666447063","https://openalex.org/W1687846465","https://openalex.org/W1836465849","https://openalex.org/W1858383477","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W1996418862","https://openalex.org/W2062118960","https://openalex.org/W2066134726","https://openalex.org/W2067529553","https://openalex.org/W2067816745","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2117539524","https://openalex.org/W2133459682","https://openalex.org/W2143449221","https://openalex.org/W2144715671","https://openalex.org/W2149172860","https://openalex.org/W2149557440","https://openalex.org/W2154652894","https://openalex.org/W2163605009","https://openalex.org/W2251583212","https://openalex.org/W2293176121","https://openalex.org/W2296385829","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W3124386704"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"the":[5,26,34,42,48,61,72,76,99,104,111],"task":[6],"of":[7,65,115],"generating":[8],"image":[9,66,117],"descriptions":[10],"with":[11,41],"gold":[12],"standard":[13],"visual":[14,49],"detections":[15],"as":[16,89],"input,":[17],"rather":[18,38],"than":[19,39],"directly":[20],"from":[21,47],"an":[22,116],"image.":[23],"This":[24],"allows":[25],"Natural":[27],"Language":[28],"Generation":[29],"community":[30],"to":[31],"focus":[32],"on":[33,75],"text":[35],"generation":[36,68,119],"process,":[37],"dealing":[40],"noise":[43],"and":[44,86],"complications":[45],"arising":[46],"detection":[50],"process.":[51],"We":[52],"propose":[53],"a":[54],"fine-grained":[55],"evaluation":[56,73],"metric":[57,74,106],"specifically":[58],"for":[59,91,109],"evaluating":[60,110],"content":[62,92,112],"selection":[63,113],"capabilities":[64],"description":[67,118],"systems.":[69],"To":[70],"demonstrate":[71],"task,":[77],"several":[78],"baselines":[79,95],"are":[80,96],"presented":[81],"using":[82,98],"bounding":[83],"box":[84],"information":[85,88],"textual":[87],"priors":[90],"selection.":[93],"The":[94],"evaluated":[97],"proposed":[100],"metric,":[101],"showing":[102],"that":[103],"finegrained":[105],"is":[107],"useful":[108],"phase":[114],"system.":[120]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
