{"id":"https://openalex.org/W4395001637","doi":"https://doi.org/10.1145/3660346","title":"Multi-grained Representation Aggregating Transformer with Gating Cycle for Change Captioning","display_name":"Multi-grained Representation Aggregating Transformer with Gating Cycle for Change Captioning","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4395001637","doi":"https://doi.org/10.1145/3660346"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660346","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3660346","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060428081","display_name":"Shengbin Yue","orcid":"https://orcid.org/0000-0002-6764-1756"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"funder","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbin Yue","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","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":"funder","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbin Tu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"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/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"funder","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China and Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China and Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"funder","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.282,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":2,"citation_normalized_percentile":{"value":0.999963,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"20","issue":"10","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9956,"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":0.9956,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9767,"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/T14011","display_name":"Elevator Systems and Control","score":0.9657,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6707269},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.45420215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8910825},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6707269},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.58767205},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45420215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22807926},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15587851},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07566312},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660346","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3660346","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Quality education","score":0.56,"id":"https://metadata.un.org/sdg/4"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62376111, U23A20388, U21B2027, 62322211"}],"datasets":[],"versions":[],"referenced_works_count":58,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1632013789","https://openalex.org/W1947481528","https://openalex.org/W1964069486","https://openalex.org/W2108598243","https://openalex.org/W2111918405","https://openalex.org/W2149006054","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2561715562","https://openalex.org/W2600463316","https://openalex.org/W2905544595","https://openalex.org/W2914393402","https://openalex.org/W2949554687","https://openalex.org/W2962793481","https://openalex.org/W2963739817","https://openalex.org/W2964196083","https://openalex.org/W2964700958","https://openalex.org/W2965628639","https://openalex.org/W2988981892","https://openalex.org/W2997383919","https://openalex.org/W3017628311","https://openalex.org/W3026458074","https://openalex.org/W3034655362","https://openalex.org/W3096808073","https://openalex.org/W3108170342","https://openalex.org/W3111947517","https://openalex.org/W3130796238","https://openalex.org/W3134875898","https://openalex.org/W3140300848","https://openalex.org/W3154362247","https://openalex.org/W3159583533","https://openalex.org/W3174377922","https://openalex.org/W3175933895","https://openalex.org/W3176470992","https://openalex.org/W3185105934","https://openalex.org/W3203526456","https://openalex.org/W3205173298","https://openalex.org/W3211865849","https://openalex.org/W4205844428","https://openalex.org/W4206621053","https://openalex.org/W4214824212","https://openalex.org/W4214920941","https://openalex.org/W4220730772","https://openalex.org/W4220790454","https://openalex.org/W4220974521","https://openalex.org/W4225289230","https://openalex.org/W4225739172","https://openalex.org/W4283688199","https://openalex.org/W4285602612","https://openalex.org/W4289537913","https://openalex.org/W4304091481","https://openalex.org/W4309938607","https://openalex.org/W4321608137","https://openalex.org/W4362013208","https://openalex.org/W4366996284","https://openalex.org/W4390871964","https://openalex.org/W4391791458"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W4310447809","https://openalex.org/W4210416330","https://openalex.org/W4200243030","https://openalex.org/W3209117276","https://openalex.org/W2800782462","https://openalex.org/W2775506363","https://openalex.org/W2748952813"],"abstract_inverted_index":{"Change":[0],"captioning":[1],"aims":[2],"to":[3,63,107,144,162,185],"describe":[4,186],"the":[5,34,41,65,72,90,95,109,122,129,133,138,146,164,177,183,187,191],"difference":[6,111,150],"within":[7],"an":[8],"image":[9],"pair":[10],"in":[11,82,190],"natural":[12],"language,":[13],"which":[14,86],"combines":[15],"visual":[16],"comprehension":[17],"and":[18,117,153,170,196,205],"language":[19,123,154],"generation.":[20],"Although":[21],"significant":[22],"progress":[23],"has":[24],"been":[25],"achieved,":[26],"it":[27],"remains":[28],"a":[29,53,83,99,126,157],"key":[30],"challenge":[31],"of":[32,93,128,135,193],"perceiving":[33],"object":[35],"change":[36,67,130,168,189,195],"from":[37,68],"different":[38],"perspectives,":[39],"especially":[40],"severe":[42],"situation":[43],"with":[44,156],"drastic":[45],"viewpoint":[46,69],"change.":[47,70,97],"In":[48],"this":[49],"article,":[50],"we":[51],"propose":[52],"novel":[54,100],"full-attentive":[55],"network,":[56],"namely":[57],"Multi-grained":[58,101],"Representation":[59,102],"Aggregating":[60],"Transformer":[61],"(MURAT),":[62],"distinguish":[64],"actual":[66,188],"Specifically,":[71],"Pair":[73],"Encoder":[74],"first":[75],"captures":[76],"similar":[77],"semantics":[78],"between":[79,149,167],"pairwise":[80],"objects":[81],"multi-level":[84],"manner,":[85],"are":[87],"regarded":[88],"as":[89,161],"semantic":[91,119,147,165],"cues":[92],"distinguishing":[94],"irrelevant":[96,194],"Next,":[98],"Aggregator":[103],"(MRA)":[104],"is":[105,142],"designed":[106],"construct":[108],"reliable":[110],"representation":[112,151],"by":[113],"employing":[114],"both":[115],"coarse-":[116],"fine-grained":[118],"cues.":[120],"Finally,":[121],"decoder":[124],"generates":[125],"description":[127],"based":[131],"on":[132,200],"output":[134],"MRA.":[136],"Besides,":[137],"Gating":[139],"Cycle":[140],"Mechanism":[141],"introduced":[143],"facilitate":[145],"consistency":[148],"learning":[152],"generation":[155],"reverse":[158],"manipulation,":[159],"so":[160],"bridge":[163],"gap":[166],"features":[169],"text":[171],"features.":[172],"Extensive":[173],"experiments":[174],"demonstrate":[175],"that":[176],"proposed":[178],"MURAT":[179],"can":[180],"greatly":[181],"improve":[182],"ability":[184],"distraction":[192],"achieves":[197],"state-of-the-art":[198],"performance":[199],"three":[201],"benchmarks,":[202],"CLEVR-Change,":[203],"CLEVR-DC,":[204],"Spot-the-Diff.":[206]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4395001637","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-03-26T20:25:07.899131","created_date":"2024-04-23"}