{"id":"https://openalex.org/W4416011362","doi":"https://doi.org/10.1109/tpami.2025.3630635","title":"Toward Visual Grounding: A Survey","display_name":"Toward Visual Grounding: A Survey","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416011362","doi":"https://doi.org/10.1109/tpami.2025.3630635","pmid":"https://pubmed.ncbi.nlm.nih.gov/41201948"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3630635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3630635","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100680501","display_name":"Linhui Xiao","orcid":"https://orcid.org/0000-0003-2592-5264"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhui Xiao","raw_affiliation_strings":["Pengcheng Laboratory (PCL), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory (PCL), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","State Key Labora tory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Labora tory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055543314","display_name":"Xiangyuan Lan","orcid":"https://orcid.org/0000-0001-8564-0346"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyuan Lan","raw_affiliation_strings":["Pengcheng Laboratory (PCL), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory (PCL), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007509238","display_name":"Yaowei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Pengcheng Laboratory (PCL), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Pengcheng Laboratory (PCL), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","State Key Labora tory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Labora tory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100680501"],"corresponding_institution_ids":["https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91133545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"48","issue":"3","first_page":"2749","last_page":"2771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.978600025177002,"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":0.978600025177002,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social 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/common-ground","display_name":"Common ground","score":0.586899995803833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5205000042915344},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4117000102996826},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.40779998898506165},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3896999955177307},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.36739999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105000019073486},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C14396502","wikidata":"https://www.wikidata.org/wiki/Q280951","display_name":"Common cause and special cause","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3630635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3630635","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41201948","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41201948","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1100260481","display_name":null,"funder_award_id":"62072455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2246614840","display_name":null,"funder_award_id":"2021ZD0112200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3087610523","display_name":null,"funder_award_id":"U23A20387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3953017609","display_name":null,"funder_award_id":"62536003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5578921854","display_name":null,"funder_award_id":"62402252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6544960559","display_name":null,"funder_award_id":"62322212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":217,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1689711448","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W2005814556","https://openalex.org/W2040145958","https://openalex.org/W2045031658","https://openalex.org/W2064675550","https://openalex.org/W2105482032","https://openalex.org/W2125447031","https://openalex.org/W2128248292","https://openalex.org/W2131774270","https://openalex.org/W2144506857","https://openalex.org/W2149557440","https://openalex.org/W2152475379","https://openalex.org/W2159149613","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2250861254","https://openalex.org/W2251329024","https://openalex.org/W2251512949","https://openalex.org/W2264742718","https://openalex.org/W2267186426","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2520141964","https://openalex.org/W2546696630","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2606473278","https://openalex.org/W2619383789","https://openalex.org/W2745461083","https://openalex.org/W2770129969","https://openalex.org/W2779827764","https://openalex.org/W2798990097","https://openalex.org/W2799263800","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2907143950","https://openalex.org/W2919115771","https://openalex.org/W2934302500","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2962749469","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2962811161","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963042258","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963323244","https://openalex.org/W2963383024","https://openalex.org/W2963445828","https://openalex.org/W2963540523","https://openalex.org/W2963614783","https://openalex.org/W2963735856","https://openalex.org/W2963783181","https://openalex.org/W2963800628","https://openalex.org/W2963876163","https://openalex.org/W2963914122","https://openalex.org/W2964022527","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966466719","https://openalex.org/W2981663434","https://openalex.org/W2984121207","https://openalex.org/W2984194315","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987401211","https://openalex.org/W2987734933","https://openalex.org/W2989176720","https://openalex.org/W3034772468","https://openalex.org/W3034952258","https://openalex.org/W3035097537","https://openalex.org/W3035561630","https://openalex.org/W3037011828","https://openalex.org/W3037533539","https://openalex.org/W3045491541","https://openalex.org/W3090449556","https://openalex.org/W3096609285","https://openalex.org/W3100393531","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3117585461","https://openalex.org/W3120329650","https://openalex.org/W3126391825","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3173220247","https://openalex.org/W3173859428","https://openalex.org/W3174004334","https://openalex.org/W3174697615","https://openalex.org/W3174965650","https://openalex.org/W3178418424","https://openalex.org/W3179041377","https://openalex.org/W3201770677","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4210606756","https://openalex.org/W4214490042","https://openalex.org/W4214650614","https://openalex.org/W4225517085","https://openalex.org/W4226104391","https://openalex.org/W4249013746","https://openalex.org/W4283688199","https://openalex.org/W4283805152","https://openalex.org/W4285192809","https://openalex.org/W4293584584","https://openalex.org/W4293868331","https://openalex.org/W4309181071","https://openalex.org/W4312331087","https://openalex.org/W4312351586","https://openalex.org/W4312446817","https://openalex.org/W4312651322","https://openalex.org/W4312660311","https://openalex.org/W4312810944","https://openalex.org/W4312815172","https://openalex.org/W4312956471","https://openalex.org/W4313068342","https://openalex.org/W4320036901","https://openalex.org/W4322766882","https://openalex.org/W4364322162","https://openalex.org/W4375869434","https://openalex.org/W4376226279","https://openalex.org/W4379929801","https://openalex.org/W4382458695","https://openalex.org/W4382464354","https://openalex.org/W4383108922","https://openalex.org/W4384820618","https://openalex.org/W4385194708","https://openalex.org/W4385245566","https://openalex.org/W4385574358","https://openalex.org/W4386065720","https://openalex.org/W4386065815","https://openalex.org/W4386071687","https://openalex.org/W4386071755","https://openalex.org/W4386075493","https://openalex.org/W4386076142","https://openalex.org/W4386076522","https://openalex.org/W4386076636","https://openalex.org/W4386523254","https://openalex.org/W4386609057","https://openalex.org/W4386790226","https://openalex.org/W4387272106","https://openalex.org/W4387969564","https://openalex.org/W4387986753","https://openalex.org/W4389104979","https://openalex.org/W4389352357","https://openalex.org/W4390872914","https://openalex.org/W4390873208","https://openalex.org/W4390873528","https://openalex.org/W4391274532","https://openalex.org/W4391451889","https://openalex.org/W4391547487","https://openalex.org/W4392904326","https://openalex.org/W4393128714","https://openalex.org/W4393159049","https://openalex.org/W4393159389","https://openalex.org/W4393934405","https://openalex.org/W4395064954","https://openalex.org/W4395080758","https://openalex.org/W4395464584","https://openalex.org/W4399541205","https://openalex.org/W4400800354","https://openalex.org/W4400949264","https://openalex.org/W4401043311","https://openalex.org/W4401607425","https://openalex.org/W4402353466","https://openalex.org/W4402660082","https://openalex.org/W4402661104","https://openalex.org/W4402671734","https://openalex.org/W4402671847","https://openalex.org/W4402703087","https://openalex.org/W4402716271","https://openalex.org/W4402716383","https://openalex.org/W4402716476","https://openalex.org/W4402727018","https://openalex.org/W4402727124","https://openalex.org/W4402728164","https://openalex.org/W4402753519","https://openalex.org/W4402753807","https://openalex.org/W4402754037","https://openalex.org/W4402754134","https://openalex.org/W4402769251","https://openalex.org/W4402952458","https://openalex.org/W4402982584","https://openalex.org/W4403081598","https://openalex.org/W4403488476","https://openalex.org/W4403617341","https://openalex.org/W4403791264","https://openalex.org/W4403990523","https://openalex.org/W4404612908","https://openalex.org/W4404643526","https://openalex.org/W4404654761","https://openalex.org/W4404691768","https://openalex.org/W4404782047","https://openalex.org/W4408352392","https://openalex.org/W4409262235","https://openalex.org/W4409366291","https://openalex.org/W4411113010","https://openalex.org/W4412389117","https://openalex.org/W4412888534","https://openalex.org/W4413146366","https://openalex.org/W4413158375","https://openalex.org/W4414197327","https://openalex.org/W4414604029","https://openalex.org/W4415795395","https://openalex.org/W4415795571","https://openalex.org/W4415797046"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Grounding,":[1,10],"also":[2],"known":[3],"as":[4,68,197,255],"Referring":[5],"Expression":[6],"Comprehension":[7],"and":[8,35,77,98,109,115,119,123,132,155,174,187,251,263],"Phrase":[9],"aims":[11],"to":[12,40,128,160,245],"ground":[13],"the":[14,18,22,29,92,117,125,138,162,182,210,217,221,229,236,265],"specific":[15],"region(s)":[16],"within":[17],"image(s)":[19],"based":[20],"on":[21],"given":[23],"expression":[24],"text.":[25],"This":[26,241],"task":[27],"simulates":[28],"common":[30,204],"referential":[31],"relationships":[32],"between":[33],"visual":[34,57,75,96,185,239],"linguistic":[36],"modalities,":[37],"enabling":[38],"machines":[39],"develop":[41],"human-like":[42],"multimodal":[43,72],"comprehension":[44],"capabilities.":[45],"Consequently,":[46],"it":[47],"has":[48,59],"extensive":[49],"applications":[50,173],"in":[51,213,235],"various":[52,126],"domains.":[53],"However,":[54],"since":[55],"2021,":[56],"grounding":[58,71,97,186],"witnessed":[60],"significant":[61],"advancements,":[62,118],"with":[63],"emerging":[64],"new":[65,84,165],"concepts":[66,108,262],"such":[67],"grounded":[69],"pre-training,":[70],"LLMs,":[73],"generalized":[74],"grounding,":[76,79],"giga-pixel":[78],"which":[80,194],"have":[81],"brought":[82],"numerous":[83,172],"challenges.":[85],"In":[86,137],"this":[87,207,226],"survey,":[88],"we":[89,141,169,180],"first":[90],"examine":[91],"developmental":[93],"history":[94],"of":[95,102,146,164,223,238],"provide":[99,156],"an":[100,256],"overview":[101,232],"essential":[103],"background":[104],"knowledge,":[105,225],"including":[106],"fundamental":[107],"evaluation":[110],"metrics.":[111],"We":[112],"systematically":[113],"track":[114],"summarize":[116],"then":[120],"meticulously":[121],"define":[122],"organize":[124],"settings":[127],"standardize":[129],"future":[130,192],"research":[131,267],"ensure":[133],"a":[134,143,151],"fair":[135,152],"comparison.":[136],"dataset":[139],"section,":[140],"compile":[142],"comprehensive":[144,231],"list":[145],"current":[147],"relevant":[148],"datasets,":[149],"conduct":[150],"comparative":[153],"analysis,":[154],"ultimate":[157],"performance":[158],"prediction":[159],"inspire":[161],"development":[163],"standard":[166],"benchmarks.":[167],"Additionally,":[168],"delve":[170],"into":[171],"highlight":[175],"several":[176],"advanced":[177],"topics.":[178],"Finally,":[179],"outline":[181],"challenges":[183],"confronting":[184],"propose":[188],"valuable":[189],"directions":[190],"for":[191,199,248,259],"research,":[193],"may":[195],"serve":[196],"inspiration":[198],"subsequent":[200],"researchers.":[201],"By":[202],"extracting":[203],"technical":[205],"details,":[206],"survey":[208,242],"encompasses":[209],"representative":[211],"work":[212],"each":[214],"subtopic":[215],"over":[216],"past":[218],"decade.":[219],"To":[220],"best":[222],"our":[224],"paper":[227],"represents":[228],"most":[230],"currently":[233],"available":[234],"field":[237],"grounding.":[240],"is":[243],"designed":[244],"be":[246],"suitable":[247],"both":[249],"beginners":[250],"experienced":[252],"researchers,":[253],"serving":[254],"invaluable":[257],"resource":[258],"understanding":[260],"key":[261],"tracking":[264],"latest":[266],"developments.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-07T00:00:00"}