{"id":"https://openalex.org/W4362013208","doi":"https://doi.org/10.1109/tmm.2023.3254162","title":"Neighborhood Contrastive Transformer for Change Captioning","display_name":"Neighborhood Contrastive Transformer for Change Captioning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362013208","doi":"https://doi.org/10.1109/tmm.2023.3254162"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3254162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3254162","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5021557044","display_name":"Yunbin Tu","orcid":"https://orcid.org/0000-0002-9525-9060"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunbin Tu","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034640518","display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088659027","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4038-753X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072833759","display_name":"Ke L\u00fc","orcid":"https://orcid.org/0000-0003-0176-3088"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lu","raw_affiliation_strings":["School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China","Peng Cheng Laboratory, Nanshan, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Nanshan, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021557044"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.7616,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92120033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"9518","last_page":"9529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9860000014305115,"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":0.9860000014305115,"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":0.9776999950408936,"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":0.9638000130653381,"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/closed-captioning","display_name":"Closed captioning","score":0.8648601770401001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.853191077709198},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6467314958572388},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5989581346511841},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5653706789016724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5378488898277283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5279715657234192},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.502417802810669},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4592658281326294},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4529414176940918},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41578954458236694},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2068275511264801},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16573652625083923},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10219526290893555}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8648601770401001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853191077709198},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6467314958572388},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5989581346511841},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5653706789016724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378488898277283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5279715657234192},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.502417802810669},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4592658281326294},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4529414176940918},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41578954458236694},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2068275511264801},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16573652625083923},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10219526290893555},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3254162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3254162","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7801426869","display_name":null,"funder_award_id":"61931008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2905544595","https://openalex.org/W2949554687","https://openalex.org/W2964196083","https://openalex.org/W2984862483","https://openalex.org/W2985775862","https://openalex.org/W2988753485","https://openalex.org/W2988981892","https://openalex.org/W3009270862","https://openalex.org/W3034221024","https://openalex.org/W3034682719","https://openalex.org/W3045147787","https://openalex.org/W3093309253","https://openalex.org/W3094673569","https://openalex.org/W3108170342","https://openalex.org/W3134875898","https://openalex.org/W3140300848","https://openalex.org/W3154362247","https://openalex.org/W3159583533","https://openalex.org/W3173961205","https://openalex.org/W3175933895","https://openalex.org/W3176470992","https://openalex.org/W3177048142","https://openalex.org/W3181758331","https://openalex.org/W3188199900","https://openalex.org/W3203526456","https://openalex.org/W3206617243","https://openalex.org/W4206621053","https://openalex.org/W4214493665","https://openalex.org/W4220790454","https://openalex.org/W4220863475","https://openalex.org/W4220974521","https://openalex.org/W4225739172","https://openalex.org/W4226397058","https://openalex.org/W4283688199","https://openalex.org/W4285169708","https://openalex.org/W4309938607","https://openalex.org/W4312344082","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6729856301","https://openalex.org/W6766978945","https://openalex.org/W6777046832","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6803537622"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W3009270862","https://openalex.org/W1516679419","https://openalex.org/W190396239"],"abstract_inverted_index":{"Change":[0],"captioning":[1],"is":[2,18,176],"to":[3,35,55,82,109,125,140],"describe":[4],"the":[5,57,93,97,135,142,159,163],"semantic":[6],"change":[7,30,44,172],"between":[8,130,138],"a":[9,51,78,105],"pair":[10],"of":[11,99],"similar":[12],"images":[13,112],"in":[14,43],"natural":[15],"language.":[16],"It":[17],"more":[19],"challenging":[20],"than":[21],"general":[22],"image":[23],"captioning,":[24],"because":[25],"it":[26],"requires":[27],"capturing":[28],"fine-grained":[29],"information":[31,129],"while":[32],"being":[33],"immune":[34],"irrelevant":[36],"viewpoint":[37],"changes,":[38],"and":[39,67,116],"solving":[40],"syntax":[41,72,150],"ambiguity":[42],"descriptions.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,75,103,133],"propose":[50],"neighborhood":[52,114],"contrastive":[53,128],"transformer":[54,143],"improve":[56],"model's":[58],"perceiving":[59],"ability":[60,69],"for":[61,70],"various":[62],"changes":[63,95],"under":[64,96],"different":[65,171],"scenes":[66],"cognition":[68],"complex":[71,149],"structure.":[73],"Concretely,":[74],"first":[76],"design":[77],"neighboring":[79,84],"feature":[80,107],"aggregating":[81],"integrate":[83],"context":[85],"into":[86],"each":[87,121],"feature,":[88],"which":[89,145],"helps":[90,146],"quickly":[91],"locate":[92],"inconspicuous":[94],"guidance":[98],"conspicuous":[100],"referents.":[101],"Then,":[102],"devise":[104],"common":[106,118],"distilling":[108],"compare":[110],"two":[111],"at":[113,178],"level":[115],"extract":[117],"properties":[119],"from":[120],"image,":[122],"so":[123],"as":[124],"learn":[126],"effective":[127],"them.":[131],"Finally,":[132],"introduce":[134],"explicit":[136],"dependencies":[137],"words":[139],"calibrate":[141],"decoder,":[144],"better":[147],"understand":[148],"structure":[151],"during":[152],"training.":[153],"Extensive":[154],"experimental":[155],"results":[156],"demonstrate":[157],"that":[158],"proposed":[160],"method":[161],"achieves":[162],"state-of-the-art":[164],"performance":[165],"on":[166],"three":[167],"public":[168],"datasets":[169],"with":[170],"scenarios.":[173],"The":[174],"code":[175],"available":[177],"<uri":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/tuyunbin/NCT</uri>":[181],".":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}