{"id":"https://openalex.org/W4404294518","doi":"https://doi.org/10.1109/m2vip62491.2024.10746112","title":"Language-guided visual attention network for visual grounding","display_name":"Language-guided visual attention network for visual grounding","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4404294518","doi":"https://doi.org/10.1109/m2vip62491.2024.10746112"},"language":"en","primary_location":{"id":"doi:10.1109/m2vip62491.2024.10746112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/m2vip62491.2024.10746112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 30th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","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/A5111339836","display_name":"Haibo Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haibo Yao","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378195","display_name":"Lipeng Wang","orcid":"https://orcid.org/0000-0002-7987-5947"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lipeng Wang","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693642","display_name":"Chengtao Cai","orcid":"https://orcid.org/0000-0002-3475-6098"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengtao Cai","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595997","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0006-4755-1194"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596827","display_name":"Zhi Zhang","orcid":"https://orcid.org/0000-0002-0785-3140"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhang","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008032235","display_name":"Lichao Jiang","orcid":"https://orcid.org/0000-0002-1125-0692"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lichao Jiang","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111339836"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20331205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9564999938011169,"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"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.920799970626831,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522477507591248},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.5644265413284302},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5294691324234009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4191078245639801},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09655401110649109},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.077181875705719},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06494390964508057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522477507591248},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5644265413284302},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5294691324234009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4191078245639801},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09655401110649109},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.077181875705719},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06494390964508057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/m2vip62491.2024.10746112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/m2vip62491.2024.10746112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 30th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","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"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2606473278","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963783181","https://openalex.org/W2963876163","https://openalex.org/W2964022527","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3174965650","https://openalex.org/W3177271687","https://openalex.org/W4214490042","https://openalex.org/W4246399668","https://openalex.org/W4323663038","https://openalex.org/W4383957015","https://openalex.org/W4384820618","https://openalex.org/W4386065755","https://openalex.org/W4387986753","https://openalex.org/W4389890864","https://openalex.org/W4389955396","https://openalex.org/W4390872680","https://openalex.org/W6620707391","https://openalex.org/W6631943919"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2021787609","https://openalex.org/W2390279801","https://openalex.org/W1537063595","https://openalex.org/W2097328689","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4234899305"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,32],"(VG)":[2,33],"is":[3,187],"a":[4,13,18,23,78,109,162,174,191],"critical":[5],"task":[6,34],"that":[7],"seeks":[8],"to":[9,29,90,112,143,168,189],"identify":[10],"and":[11,46,64,103,116,158],"localize":[12],"specific":[14],"visual":[15,31,63,80,84,93,137,157],"region":[16],"within":[17],"given":[19],"image":[20],"based":[21],"on":[22,179],"corresponding":[24],"referring":[25],"expression.":[26],"Existing":[27],"approaches":[28],"the":[30,57,62,69,99,114,123,130,135,145,170,180],"can":[35,87,121],"be":[36],"categorized":[37],"into":[38],"three":[39],"main":[40],"types:":[41],"two-stage":[42],"methods,":[43,45,48],"one-stage":[44],"Transformer-based":[47],"which":[49,86,120,140],"have":[50],"achieved":[51],"high":[52],"performance.":[53],"However,":[54],"most":[55],"of":[56,71,98,147,155,165,176],"methods":[58],"do":[59],"not":[60],"exploit":[61],"linguistic":[65,118,124,159],"information":[66,94,125,167],"well,":[67],"limiting":[68],"performance":[70,193],"model.":[72],"In":[73,149,173],"this":[74],"work,":[75],"we":[76,106,133,151],"propose":[77],"language-guided":[79],"attention":[81,138,146],"network":[82],"for":[83],"grounding,":[85],"utilize":[88,107],"language":[89,142],"deeply":[91],"explore":[92],"by":[95,129],"better":[96,163],"processing":[97],"relationship":[100],"between":[101],"vision":[102],"language.":[104],"Specifically,":[105],"BERT,":[108],"pre-trained":[110],"model,":[111],"get":[113],"word-level":[115],"sentence-level":[117],"features,":[119,160],"understand":[122],"more":[126],"comprehensively.":[127],"Inspired":[128],"Transformer":[131],"architecture,":[132],"design":[134],"stacked":[136],"module,":[139],"leverages":[141],"direct":[144],"vision.":[148],"addition,":[150],"discuss":[152],"several":[153],"ways":[154],"fusing":[156],"enabling":[161],"fusion":[164],"visual-linguistic":[166],"obtain":[169],"correct":[171],"coordinates.":[172],"series":[175],"comprehensive":[177],"evaluations":[178],"ReferItGame":[181],"benchmark":[182],"dataset,":[183],"our":[184],"proposed":[185],"model":[186],"shown":[188],"establish":[190],"new":[192],"standard.":[194]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}