{"id":"https://openalex.org/W4415709687","doi":"https://doi.org/10.1109/icme59968.2025.11210178","title":"A Simple and Better Baseline for Visual Grounding","display_name":"A Simple and Better Baseline for Visual Grounding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709687","doi":"https://doi.org/10.1109/icme59968.2025.11210178"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5028904438","display_name":"Jingchao Wang","orcid":"https://orcid.org/0000-0003-1848-320X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchao Wang","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040944809","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0002-9654-260X"},"institutions":[{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Shanghai AI Laboratory,OpenScience Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,OpenScience Lab,Shanghai,China","institution_ids":["https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101940253","display_name":"Dingjiang Huang","orcid":"https://orcid.org/0000-0002-0144-7344"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingjiang Huang","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449116","display_name":"Hongfei Wang","orcid":"https://orcid.org/0000-0002-8162-9243"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Wang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Life Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Life Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051649145","display_name":"Yefeng Zheng","orcid":"https://orcid.org/0000-0003-2195-2847"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Westlake University,Medical Artificial Intelligence Laboratory,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University,Medical Artificial Intelligence Laboratory,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9818999767303467,"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":0.9818999767303467,"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":0.006099999882280827,"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":0.0015999999595806003,"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/feature","display_name":"Feature (linguistics)","score":0.6258999705314636},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5446000099182129},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.515500009059906},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48539999127388},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4821000099182129},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312999725341797},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2946086442","https://openalex.org/W2964284374","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3192448690","https://openalex.org/W3207127495","https://openalex.org/W4214490042","https://openalex.org/W4309181071","https://openalex.org/W4312351586","https://openalex.org/W4382458695","https://openalex.org/W4384820618","https://openalex.org/W4385245566","https://openalex.org/W4386071652","https://openalex.org/W4386076636","https://openalex.org/W4387272106","https://openalex.org/W4387623721","https://openalex.org/W4392543666","https://openalex.org/W4393156126","https://openalex.org/W4393159389","https://openalex.org/W4402716271","https://openalex.org/W4402716371","https://openalex.org/W4402716383","https://openalex.org/W4402727388"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"grounding":[1],"aims":[2],"to":[3,40,67,123,139,156],"predict":[4],"the":[5,33,42,78,101,117,125,141,145,175,187],"locations":[6],"of":[7],"target":[8],"objects":[9],"specified":[10],"by":[11],"textual":[12],"descriptions.":[13],"For":[14],"this":[15,81],"task":[16],"with":[17],"linguistic":[18,61,102,128],"and":[19,57,63,103,115,130,184],"visual":[20,35,64,93,104,131,136,146,160],"modalities,":[21],"there":[22],"is":[23,50,192],"a":[24,71,85,151,179],"latest":[25],"research":[26],"line":[27],"that":[28,174],"focuses":[29],"on":[30,53,168],"only":[31,157],"selecting":[32],"linguistic-relevant":[34],"regions":[36],"for":[37,92,133,162],"object":[38],"localization":[39],"reduce":[41,140],"computational":[43,142],"overhead.":[44,75],"Albeit":[45],"achieving":[46],"impressive":[47],"performance,":[48],"it":[49],"iteratively":[51],"performed":[52],"different":[54],"image":[55],"scales,":[56],"at":[58,194],"every":[59],"iteration,":[60],"features":[62,65,161],"need":[66],"be":[68],"stored":[69],"in":[70,80,119],"cache,":[72],"incurring":[73],"extra":[74],"To":[76],"facilitate":[77,124],"implementation,":[79],"paper,":[82],"we":[83,98,149],"propose":[84],"feature":[86,147,153],"selection-based":[87],"simple":[88],"yet":[89],"effective":[90,135],"baseline":[91],"grounding,":[94],"called":[95],"FSVG.":[96],"Specifically,":[97],"directly":[99],"encapsulate":[100],"modalities":[105],"into":[106],"an":[107],"overall":[108],"network":[109],"architecture":[110],"without":[111],"complicated":[112],"iterative":[113],"procedures,":[114],"utilize":[116],"language":[118],"parallel":[120],"as":[121],"guidance":[122],"interaction":[126],"between":[127,182],"modal":[129,132],"extracting":[134],"features.":[137],"Furthermore,":[138],"cost,":[143],"during":[144],"learning,":[148],"introduce":[150],"similarity-based":[152],"selection":[154],"mechanism":[155],"exploit":[158],"language-related":[159],"faster":[163],"prediction.":[164],"Extensive":[165],"experiments":[166],"conducted":[167],"several":[169],"benchmark":[170],"datasets":[171],"comprehensively":[172],"substantiate":[173],"proposed":[176],"FSVG":[177],"achieves":[178],"better":[180],"balance":[181],"accuracy":[183],"efficiency":[185],"beyond":[186],"current":[188],"state-of-the-art":[189],"methods.":[190],"Code":[191],"available":[193],"https://github.com/jcwang0602/FSVG.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}