{"id":"https://openalex.org/W2889017949","doi":"https://doi.org/10.18653/v1/d18-1436","title":"Learning to Describe Differences Between Pairs of Similar Images","display_name":"Learning to Describe Differences Between Pairs of Similar Images","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889017949","doi":"https://doi.org/10.18653/v1/d18-1436","mag":"2889017949"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1436","pdf_url":"https://www.aclweb.org/anthology/D18-1436.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1436.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015256182","display_name":"Harsh Jhamtani","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"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsh Jhamtani","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University","Adobe Systems (United States), San Jose, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Adobe Systems (United States), San Jose, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4024","last_page":"4034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"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":0.8273138999938965},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.7570242285728455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7345372438430786},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6173331141471863},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6094517707824707},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5794764161109924},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5368571281433105},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48335760831832886},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42302945256233215},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39453285932540894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3487105369567871},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3315577507019043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273138999938965},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.7570242285728455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7345372438430786},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6173331141471863},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6094517707824707},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5794764161109924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5368571281433105},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48335760831832886},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42302945256233215},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39453285932540894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3487105369567871},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3315577507019043},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1436","pdf_url":"https://www.aclweb.org/anthology/D18-1436.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.10584","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.10584","pdf_url":"https://arxiv.org/pdf/1808.10584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.1808.10584","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.10584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2889017949","is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/1808.10584","pdf_url":null,"source":{"id":"https://openalex.org/S4306417987","display_name":"Computer Vision and Pattern Recognition","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Computer Vision and Pattern Recognition","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1436","pdf_url":"https://www.aclweb.org/anthology/D18-1436.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889017949.pdf","grobid_xml":"https://content.openalex.org/works/W2889017949.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1577877742","https://openalex.org/W1673310716","https://openalex.org/W1843891098","https://openalex.org/W1956340063","https://openalex.org/W2006969979","https://openalex.org/W2064675550","https://openalex.org/W2081056190","https://openalex.org/W2101105183","https://openalex.org/W2101234009","https://openalex.org/W2112053844","https://openalex.org/W2133459682","https://openalex.org/W2160544350","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2337353209","https://openalex.org/W2463565445","https://openalex.org/W2523790121","https://openalex.org/W2547811817","https://openalex.org/W2558535589","https://openalex.org/W2561658355","https://openalex.org/W2729842244","https://openalex.org/W2798273548","https://openalex.org/W2798504462","https://openalex.org/W2899771611","https://openalex.org/W2950178297","https://openalex.org/W2950401034","https://openalex.org/W2950761309","https://openalex.org/W2962811161","https://openalex.org/W2963084599","https://openalex.org/W2963109634","https://openalex.org/W2963389687","https://openalex.org/W2963656855","https://openalex.org/W2964322208","https://openalex.org/W3098232790"],"related_works":["https://openalex.org/W2964196083","https://openalex.org/W3047113405","https://openalex.org/W2757315180","https://openalex.org/W2981161748","https://openalex.org/W2951410032","https://openalex.org/W2891424527","https://openalex.org/W2115628259","https://openalex.org/W2949645788","https://openalex.org/W3140002740","https://openalex.org/W1575391927","https://openalex.org/W2953288085","https://openalex.org/W3208700264","https://openalex.org/W3120182027","https://openalex.org/W3093136537","https://openalex.org/W2185824099","https://openalex.org/W2522861532","https://openalex.org/W2949166814","https://openalex.org/W2979773121","https://openalex.org/W2952115249","https://openalex.org/W2156867888"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"the":[5,13,44,136,140],"task":[6],"of":[7,30,92,117],"automatically":[8],"generating":[9],"text":[10],"to":[11,40,59,114],"describe":[12,42],"differences":[14,45],"between":[15],"two":[16],"similar":[17],"images.":[18],"We":[19,83,101,123],"collect":[20],"a":[21,47,51,76,85,96,103,111],"new":[22],"dataset":[23,55,72],"by":[24,109],"crowd-sourcing":[25],"difference":[26],"descriptions":[27],"for":[28,79,98,126],"pairs":[29],"image":[31],"frames":[32],"extracted":[33],"from":[34],"video-surveillance":[35],"footage.":[36],"Annotators":[37],"were":[38],"asked":[39],"succinctly":[41],"all":[43],"in":[46],"short":[48],"paragraph.":[49],"As":[50],"result,":[52],"our":[53],"novel":[54],"provides":[56],"an":[57],"opportunity":[58],"explore":[60],"models":[61,141],"that":[62,89,105,142],"align":[63,115],"language":[64],"and":[65,67,130],"vision,":[66],"capture":[68],"visual":[69,87,107],"salience.":[70],"The":[71],"may":[73],"also":[74],"be":[75],"useful":[77],"benchmark":[78],"coherent":[80],"multi-sentence":[81,134],"generation.":[82],"perform":[84],"firstpass":[86],"analysis":[88],"exposes":[90],"clusters":[91,116],"differing":[93,118],"pixels":[94,119],"as":[95,131,133],"proxy":[97],"object-level":[99],"differences.":[100],"propose":[102],"model":[104,138],"captures":[106],"salience":[108],"using":[110],"latent":[112],"variable":[113],"with":[120],"output":[121],"sentences.":[122],"find":[124],"that,":[125],"both":[127],"single-sentence":[128],"generation":[129],"well":[132],"generation,":[135],"proposed":[137],"outperforms":[139],"use":[143],"attention":[144],"alone.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}