{"id":"https://openalex.org/W4391791458","doi":"https://doi.org/10.1109/tpami.2024.3365104","title":"SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning","display_name":"SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning","publication_year":2024,"publication_date":"2024-02-13","ids":{"openalex":"https://openalex.org/W4391791458","doi":"https://doi.org/10.1109/tpami.2024.3365104","pmid":"https://pubmed.ncbi.nlm.nih.gov/38349824"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3365104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3365104","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5115601581","display_name":"Li Su","orcid":"https://orcid.org/0000-0001-5358-2786"},"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":"Li Su","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","Peng Cheng Laboratory, Shenzhen, 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":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"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":"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":10.2207,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.988747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"7","first_page":"4926","last_page":"4943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9824000000953674,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9564999938011169,"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":0.7606590986251831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5839373469352722},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5284735560417175},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5264471173286438},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49959397315979004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44764846563339233},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.44631513953208923},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4144403040409088},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3364911675453186},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18350815773010254},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08736220002174377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606590986251831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839373469352722},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5284735560417175},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5264471173286438},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49959397315979004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44764846563339233},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.44631513953208923},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4144403040409088},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3364911675453186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18350815773010254},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08736220002174377},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3365104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3365104","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38349824","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38349824","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1883487206","display_name":null,"funder_award_id":"62336008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4536128632","display_name":null,"funder_award_id":"62322211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G575396328","display_name":null,"funder_award_id":"62225207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G6251355785","display_name":null,"funder_award_id":"2020108","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"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"},{"id":"https://openalex.org/G8573909329","display_name":null,"funder_award_id":"E2ET1104","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W1996430422","https://openalex.org/W2042323109","https://openalex.org/W2101105183","https://openalex.org/W2138055993","https://openalex.org/W2194775991","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2765658575","https://openalex.org/W2766261529","https://openalex.org/W2905544595","https://openalex.org/W2949554687","https://openalex.org/W2964196083","https://openalex.org/W2988981892","https://openalex.org/W3009270862","https://openalex.org/W3034871396","https://openalex.org/W3047153790","https://openalex.org/W3093309253","https://openalex.org/W3108170342","https://openalex.org/W3140300848","https://openalex.org/W3149106692","https://openalex.org/W3159583533","https://openalex.org/W3167939936","https://openalex.org/W3175933895","https://openalex.org/W3176470992","https://openalex.org/W3203701986","https://openalex.org/W4205844428","https://openalex.org/W4206621053","https://openalex.org/W4220790454","https://openalex.org/W4220863475","https://openalex.org/W4220974521","https://openalex.org/W4225739172","https://openalex.org/W4283688199","https://openalex.org/W4297808394","https://openalex.org/W4304091481","https://openalex.org/W4309938607","https://openalex.org/W4312383651","https://openalex.org/W4313186260","https://openalex.org/W4321608137","https://openalex.org/W4362013208","https://openalex.org/W4366996284","https://openalex.org/W4385245566","https://openalex.org/W4390871964","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6766978945","https://openalex.org/W6767194493","https://openalex.org/W6780226713","https://openalex.org/W6839224452","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W4281476908"],"abstract_inverted_index":{"Change":[0],"captioning":[1],"aims":[2],"to":[3,23,59,79,110,152,218,245,252],"describe":[4],"the":[5,16,24,35,40,57,62,67,93,113,124,132,161,164,171,177,180,186,190,193,206,220,237,243,264,268,272],"semantic":[6,172],"change":[7,21,44,64,82,94,173,198],"between":[8,92,179],"two":[9,139],"similar":[10],"images.":[11],"In":[12,69],"this":[13,70],"process,":[14],"as":[15,151,251],"most":[17],"typical":[18],"distractor,":[19],"viewpoint":[20,120],"leads":[22],"pseudo":[25],"changes":[26,115],"about":[27,167,258],"appearance":[28],"and":[29,87,96,128,169,185,212],"position":[30,130],"of":[31,43,126,134,182,209,239],"objects,":[32],"thereby":[33],"overwhelming":[34],"real":[36],"change.":[37,259],"Besides,":[38],"since":[39],"visual":[41,216,225,229],"signal":[42],"appears":[45],"in":[46],"a":[47,74,103,155,214,254],"local":[48],"region":[49],"with":[50,163],"weak":[51],"feature,":[52],"it":[53],"is":[54,108],"difficult":[55],"for":[56,200],"model":[58,162,194],"directly":[60],"translate":[61],"learned":[63],"features":[65,83,95,133,199],"into":[66,131],"sentence.":[68],"paper,":[71],"we":[72,204],"propose":[73],"syntax-calibrated":[75],"multi-aspect":[76,104],"relation":[77,105,178],"transformer":[78,221],"learn":[80,138,196],"effective":[81,197],"under":[84,116],"different":[85,232],"scenes,":[86],"build":[88,246],"reliable":[89,247],"cross-modal":[90,248],"alignment":[91,148],"linguistic":[97,256],"words":[98],"during":[99,231],"caption":[100,201],"generation.":[101,202],"Specifically,":[102],"learning":[106],"network":[107],"designed":[109],"1)":[111],"explore":[112],"fine-grained":[114],"irrelevant":[117],"distractors":[118],"(e.g.,":[119],"change)":[121],"by":[122,143,175],"embedding":[123],"relations":[125],"semantics":[127],"relative":[129],"each":[135],"image;":[136],"2)":[137],"view-invariant":[140],"image":[141,187],"representations":[142,181],"strengthening":[144],"their":[145],"global":[146],"contrastive":[147],"relation,":[149],"so":[150,250],"help":[153],"capture":[154],"stable":[156],"difference":[157,184],"representation;":[158],"3)":[159],"provide":[160],"prior":[165],"knowledge":[166,208],"whether":[168],"where":[170],"happened":[174],"measuring":[176],"captured":[183],"pair.":[188],"Through":[189],"above":[191],"manner,":[192],"can":[195],"Further,":[203],"introduce":[205],"syntax":[207],"Part-of-Speech":[210],"(POS)":[211],"devise":[213],"POS-based":[215,224],"switch":[217,226],"calibrate":[219],"decoder.":[222],"The":[223],"dynamically":[227],"utilizes":[228],"information":[230],"word":[233],"generation":[234],"based":[235],"on":[236,271],"POS":[238],"words.":[240],"This":[241],"enables":[242],"decoder":[244],"alignment,":[249],"generate":[253],"high-level":[255],"sentence":[257],"Extensive":[260],"experiments":[261],"show":[262],"that":[263],"proposed":[265],"method":[266],"achieves":[267],"state-of-the-art":[269],"performance":[270],"three":[273],"public":[274],"datasets.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":16}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
