{"id":"https://openalex.org/W4392904553","doi":"https://doi.org/10.1109/icassp48485.2024.10447732","title":"Memory Self-Calibrated Network for Visual Grounding","display_name":"Memory Self-Calibrated Network for Visual Grounding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904553","doi":"https://doi.org/10.1109/icassp48485.2024.10447732"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447732","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100440218","display_name":"Jie Wu","orcid":"https://orcid.org/0009-0006-5333-011X"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Wu","raw_affiliation_strings":["China University of Petroleum (East China)"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China)","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072254497","display_name":"Chunlei Wu","orcid":"https://orcid.org/0000-0002-0944-2564"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Wu","raw_affiliation_strings":["China University of Petroleum (East China)"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China)","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059464565","display_name":"Yiwei Wei","orcid":"https://orcid.org/0000-0002-7627-5487"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Wei","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631481","display_name":"Xiuxuan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuxuan Shen","raw_affiliation_strings":["Xidian University"],"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031199063","display_name":"Leiquan Wang","orcid":"https://orcid.org/0000-0003-4314-0030"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leiquan Wang","raw_affiliation_strings":["China University of Petroleum (East China)"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China)","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100440218"],"corresponding_institution_ids":["https://openalex.org/I4210162190"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02717479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4155","last_page":"4159"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976000189781189,"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":0.8095930814743042},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5961579084396362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749844908714294},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5541344881057739},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4964926838874817},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4819316864013672},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4693354666233063},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4591199457645416},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4453514516353607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3865017890930176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095930814743042},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5961579084396362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749844908714294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5541344881057739},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4964926838874817},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4819316864013672},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4693354666233063},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4591199457645416},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4453514516353607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3865017890930176},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447732","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2962764817","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3110435696","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3182736162","https://openalex.org/W3192448690","https://openalex.org/W4214490042","https://openalex.org/W4283029876","https://openalex.org/W4293584584","https://openalex.org/W4309181071","https://openalex.org/W4385569851"],"related_works":["https://openalex.org/W2085384747","https://openalex.org/W2088166309","https://openalex.org/W1891216533","https://openalex.org/W4312133475","https://openalex.org/W4238976562","https://openalex.org/W2276587472","https://openalex.org/W2615795876","https://openalex.org/W2049612369","https://openalex.org/W4236696095","https://openalex.org/W2770872919"],"abstract_inverted_index":{"Visual":[0],"Grounding":[1],"(VG)":[2],"aims":[3],"to":[4,16,31,45,101,120,133,154],"locate":[5],"the":[6,38,71,75,104,121,135,139,148],"most":[7],"relevant":[8],"object":[9],"or":[10],"region":[11],"in":[12,23,40],"an":[13],"image":[14,27,42,67,107,115,131],"according":[15,44],"a":[17,58],"natural":[18],"language":[19],"query.":[20],"Existing":[21],"methods":[22],"VG":[24],"utilize":[25],"fixed":[26],"and":[28,49,80,95,108],"text":[29],"representations":[30,43,68,128],"capture":[32],"cross-modal":[33],"semantic":[34,76],"consistency,":[35],"which":[36],"limits":[37],"flexibility":[39],"adjusting":[41],"diverse":[46],"textual":[47],"information":[48,116],"hinders":[50],"performance.":[51],"To":[52],"handle":[53],"this":[54],"limitation,":[55],"we":[56,86],"propose":[57],"novel":[59],"Memory":[60,97],"Self-Calibrated":[61],"Network":[62],"(MSCN)":[63],"by":[64],"dynamically":[65],"refining":[66],"based":[69],"on":[70,112,144],"query,":[72,122],"thereby":[73],"improving":[74],"consistency":[77],"between":[78,106],"texts":[79],"images":[81],"for":[82],"visual":[83],"grounding.":[84],"Specifically,":[85],"introduce":[87],"two":[88],"modules:":[89],"Semantic":[90],"Relevance":[91],"Filtering":[92],"Module":[93,99],"(SRFM)":[94],"Adaptive":[96],"Fusion":[98],"(AMFM),":[100],"explicitly":[102],"model":[103],"relationship":[105],"text.":[109],"SRFM":[110],"focuses":[111],"filtering":[113],"out":[114],"that":[117],"is":[118],"irrelevant":[119],"while":[123],"AMFM":[124],"adaptively":[125],"fuses":[126],"text-related":[127],"with":[129],"initial":[130],"features":[132],"enhance":[134],"understanding":[136],"ability":[137],"of":[138,150],"MSCN":[140],"model.":[141],"Comprehensive":[142],"experiments":[143],"three":[145],"datasets":[146],"demonstrate":[147],"superiority":[149],"our":[151],"method":[152],"compared":[153],"existing":[155],"approaches.":[156]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}