{"id":"https://openalex.org/W4372260221","doi":"https://doi.org/10.1109/icassp49357.2023.10095662","title":"Background Disturbance Mitigation for Video Captioning Via Entity-Action Relocation","display_name":"Background Disturbance Mitigation for Video Captioning Via Entity-Action Relocation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260221","doi":"https://doi.org/10.1109/icassp49357.2023.10095662"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101709965","display_name":"Zipeng Li","orcid":"https://orcid.org/0000-0002-4785-8640"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zipeng Li","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736130","display_name":"Shuqin Chen","orcid":"https://orcid.org/0000-0003-3436-653X"},"institutions":[{"id":"https://openalex.org/I4210154851","display_name":"Hubei University of Education","ror":"https://ror.org/04f41cb79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154851"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Chen","raw_affiliation_strings":["Hubei University of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei University of Education","institution_ids":["https://openalex.org/I4210154851"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564554","display_name":"Wenxuan Liu","orcid":"https://orcid.org/0000-0002-1528-4224"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Liu","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949151","display_name":"Wenxin Huang","orcid":"https://orcid.org/0000-0001-8683-7327"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Huang","raw_affiliation_strings":["Hubei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei University","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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":0.9955000281333923,"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":0.8738967180252075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827288031578064},{"id":"https://openalex.org/keywords/relocation","display_name":"Relocation","score":0.6409627199172974},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5965522527694702},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5622771978378296},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4996495246887207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4923206567764282},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4462055563926697},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.42740699648857117},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.41915518045425415},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4148363471031189},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.411133736371994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39521145820617676},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3726474642753601},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3628801107406616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09782320261001587},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06977406144142151}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8738967180252075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827288031578064},{"id":"https://openalex.org/C2779019381","wikidata":"https://www.wikidata.org/wiki/Q3499564","display_name":"Relocation","level":2,"score":0.6409627199172974},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5965522527694702},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5622771978378296},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4996495246887207},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4923206567764282},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4462055563926697},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.42740699648857117},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.41915518045425415},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4148363471031189},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.411133736371994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39521145820617676},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3726474642753601},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3628801107406616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09782320261001587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06977406144142151},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/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/icassp49357.2023.10095662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2842511635","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2984862483","https://openalex.org/W3009192917","https://openalex.org/W3034221024","https://openalex.org/W3034593503","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3039060838","https://openalex.org/W3093309253","https://openalex.org/W3115684750","https://openalex.org/W3171155871","https://openalex.org/W3176425931","https://openalex.org/W3181598125","https://openalex.org/W4224920290","https://openalex.org/W4224933795","https://openalex.org/W4297808394","https://openalex.org/W4382464395","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2046732476","https://openalex.org/W2486027828","https://openalex.org/W4210416330","https://openalex.org/W2034964907","https://openalex.org/W2380877425","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2147260044","https://openalex.org/W4290852288","https://openalex.org/W2365744358"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,6,24,33,58,83,91,116,129,145],"generate":[4],"sentences":[5],"accurately":[7],"describe":[8],"the":[9,17,50,62,65,85,97,131,135,140,147,151,160,165],"video":[10,14,27,55,72,104,120,167,185],"content,":[11],"in":[12],"which":[13,37],"background":[15,56,110,182],"plays":[16],"role":[18],"of":[19,54,87,134,139,154,164],"prompts.":[20],"State-of-the-art":[21],"methods":[22],"tend":[23],"explore":[25],"richer":[26],"representations":[28,137,142],"adequately,":[29],"fusing":[30],"with":[31,181],"language":[32],"improve":[34],"caption":[35,59,133,153,190],"quality,":[36],"has":[38],"shown":[39],"great":[40],"success.":[41],"However,":[42],"they":[43],"focus":[44],"on":[45,159,171],"exploiting":[46],"foreground":[47],"semantics,":[48],"ignoring":[49],"potential":[51],"negative":[52],"impact":[53],"disturbance":[57,183],"generation,":[60],"i.e.,":[61],"entities":[63,88,113,161],"and":[64,89,114,138,144,162,176],"actions":[66,90,115,163],"are":[67],"misjudged":[68],"by":[69,94],"a":[70,108,118,188],"similar":[71],"background.":[73,98],"To":[74],"ameliorate":[75],"this":[76],"issue,":[77],"we":[78,106],"propose":[79],"Entity-Action":[80],"Relocation":[81],"(EAR)":[82],"enhance":[84],"adaptability":[86],"various":[92],"backgrounds":[93],"giving":[95],"them":[96],"Specifically,":[99],"for":[100,111,184],"an":[101],"extracted":[102],"original":[103,136],"feature,":[105],"construct":[107],"mixed":[109],"all":[112],"form":[117],"distracting":[119,141],"feature":[121],"sample.":[122],"After":[123],"that,":[124],"contrastive":[125],"learning":[126],"is":[127],"applied":[128],"pull":[130],"generated":[132,152],"closer,":[143],"push":[146],"former":[148],"away":[149],"from":[150],"other":[155],"videos,":[156],"explicitly":[157],"concentrating":[158],"current":[166],"scene.":[168],"Extensive":[169],"experiments":[170],"two":[172],"public":[173],"datasets":[174],"(MSR-VTT":[175],"MSVD)":[177],"demonstrate":[178],"that":[179],"dealing":[180],"can":[186],"obtain":[187],"competitive":[189],"generation":[191],"effect.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
