{"id":"https://openalex.org/W4399423264","doi":"https://doi.org/10.1145/3652583.3658002","title":"MFVG: A Visual Grounding Network with Multi-scale Fusion","display_name":"MFVG: A Visual Grounding Network with Multi-scale Fusion","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423264","doi":"https://doi.org/10.1145/3652583.3658002"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658002","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004699482","display_name":"Peijia Chen","orcid":"https://orcid.org/0009-0005-1743-2074"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peijia Chen","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1743-2074","affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040889357","display_name":"Ke Qi","orcid":"https://orcid.org/0000-0003-1543-6598"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Qi","raw_affiliation_strings":["School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6598","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030065834","display_name":"Xi Tao","orcid":"https://orcid.org/0009-0002-1314-1729"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Tao","raw_affiliation_strings":["School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-1314-1729","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101666720","display_name":"Wenhao Xu","orcid":"https://orcid.org/0009-0007-5826-3486"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Xu","raw_affiliation_strings":["School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-5826-3486","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineer, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103143351","display_name":"Jingdong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Zhang","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-4702-7686","affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004699482"],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07004395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"713","last_page":"721"},"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":0.9980999827384949,"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":0.8356398344039917},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6666125059127808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329824924468994},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6074842214584351},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5972051024436951},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5774132013320923},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5702537298202515},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5444494485855103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46972620487213135},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4692905843257904},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43275997042655945},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4265028238296509},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4159086048603058},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41392752528190613},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3817848563194275},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.18694952130317688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356398344039917},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6666125059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329824924468994},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6074842214584351},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5972051024436951},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5774132013320923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5702537298202515},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5444494485855103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46972620487213135},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4692905843257904},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43275997042655945},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4265028238296509},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4159086048603058},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41392752528190613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3817848563194275},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.18694952130317688},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658002","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658002","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423264.pdf","grobid_xml":"https://content.openalex.org/works/W4399423264.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2565639579","https://openalex.org/W2606473278","https://openalex.org/W2620365397","https://openalex.org/W2946086442","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963389687","https://openalex.org/W2963783181","https://openalex.org/W2963857746","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3163747765","https://openalex.org/W3173364567","https://openalex.org/W4214490042","https://openalex.org/W4309181071","https://openalex.org/W4312351586","https://openalex.org/W4313145013","https://openalex.org/W4386590759"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W3090872036","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4287868219"],"abstract_inverted_index":{"Visual":[0],"grounding,":[1],"as":[2],"a":[3,99],"crucial":[4],"multimodal":[5,27,43,93],"reasoning":[6,30],"task,":[7],"aims":[8],"to":[9,25,134,147,187],"locate":[10],"target":[11],"objects":[12],"in":[13],"images":[14],"based":[15,106],"on":[16,36,107,172],"natural":[17],"language":[18,133],"queries.":[19,122],"This":[20,95],"task":[21],"requires":[22],"the":[23,59,63,71,77,86,126,157,161,191],"model":[24,162],"perform":[26],"fusion":[28,44,109],"and":[29,38,45,82,101,132,137,152,163],"effectively.":[31],"Early":[32],"methods":[33,49],"often":[34],"rely":[35],"complex":[37],"manually":[39],"designed":[40],"modules":[41],"for":[42,53,92],"reasoning.":[46,94],"However,":[47],"these":[48],"are":[50],"usually":[51],"customized":[52],"certain":[54],"specific":[55],"scenarios,":[56],"thus":[57],"limiting":[58],"generalization":[60],"ability":[61,159],"of":[62,88,130,160],"model.":[64],"Recent":[65],"works":[66],"achieve":[67],"visual":[68,103,115,166],"grounding":[69,104],"through":[70,120],"attention":[72],"mechanism,":[73],"which":[74,113],"can":[75],"capture":[76,148],"alignment":[78],"relationship":[79],"between":[80],"vision":[81,131],"language,":[83],"but":[84],"ignore":[85],"importance":[87],"different":[89,141],"scale":[90],"features":[91,116,139,151],"paper":[96],"proposes":[97],"MFVG,":[98],"concise":[100],"effective":[102],"framework":[105],"multiscale":[108],"guided":[110,143],"by":[111,144],"texts,":[112],"learns":[114],"with":[117,190],"discriminative":[118],"semantics":[119],"text":[121,145],"Specifically,":[123],"MFVG":[124,184],"allows":[125],"contextual":[127],"semantic":[128,153],"information":[129],"interact":[135],"fully":[136],"fuses":[138],"at":[140],"scales":[142],"queries":[146],"richer":[149],"detail":[150],"information,":[154],"thereby":[155],"enhancing":[156],"representational":[158],"achieving":[164],"better":[165],"grounding.":[167],"We":[168],"conducted":[169],"extensive":[170],"experiments":[171],"five":[173],"widely":[174],"used":[175],"benchmarks.":[176],"The":[177],"experiment":[178],"results":[179],"show":[180],"that":[181],"our":[182],"proposed":[183],"is":[185],"superior":[186],"or":[188],"comparable":[189],"state-of-the-art":[192],"methods.":[193]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}