{"id":"https://openalex.org/W4414942198","doi":"https://doi.org/10.1109/iccv51701.2025.02145","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","display_name":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414942198","doi":"https://doi.org/10.1109/iccv51701.2025.02145"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101971204","display_name":"Rui Hu","orcid":"https://orcid.org/0000-0002-5987-4277"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Hu","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109772253","display_name":"L. X. Zhu","orcid":"https://orcid.org/0009-0008-4054-6354"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghui Zhu","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113228098","display_name":"Yuxuan Zhang","orcid":"https://orcid.org/0000-0001-9783-0323"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Zhang","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022657064","display_name":"Tianheng Cheng","orcid":"https://orcid.org/0009-0003-4100-1659"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianheng Cheng","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349532","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0002-2121-6615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["vivo AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109741159","display_name":"Heng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Liu","raw_affiliation_strings":["vivo AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041730525","display_name":"Longjin Ran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longjin Ran","raw_affiliation_strings":["vivo AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674291","display_name":"Xiaoxin Chen","orcid":"https://orcid.org/0000-0002-7817-7215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxin Chen","raw_affiliation_strings":["vivo AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665054","display_name":"Wenyu Liu","orcid":"https://orcid.org/0000-0002-0244-3038"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Liu","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinggang Wang","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"23105","last_page":"23114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12424","display_name":"Earthquake Detection and Analysis","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12424","display_name":"Earthquake Detection and Analysis","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13018","display_name":"Seismology and Earthquake Studies","score":0.9768999814987183,"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"}},{"id":"https://openalex.org/T11757","display_name":"Seismic Waves and Analysis","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.802299976348877},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7549999952316284},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5964000225067139},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49880000948905945},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.489300012588501},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.43619999289512634}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.802299976348877},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7549999952316284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487999796867371},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770999789237976},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10596","pdf_url":"https://arxiv.org/pdf/2503.10596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.10596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10596","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10596","pdf_url":"https://arxiv.org/pdf/2503.10596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5611001984","display_name":null,"funder_award_id":"62276108","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pixel":[0],"grounding,":[1],"encompassing":[2,81],"tasks":[3],"such":[4],"as":[5],"Referring":[6],"Expression":[7],"Segmentation":[8],"(RES),":[9],"has":[10],"garnered":[11],"considerable":[12],"attention":[13],"due":[14],"to":[15,115,142],"its":[16],"immense":[17],"potential":[18],"for":[19],"bridging":[20],"the":[21,134,143],"gap":[22],"between":[23],"vision":[24],"and":[25,49,87,91,126],"language":[26],"modalities.":[27],"However,":[28],"advancements":[29],"in":[30,39],"this":[31],"domain":[32],"are":[33],"currently":[34],"constrained":[35],"by":[36],"limitations":[37],"inherent":[38],"existing":[40],"datasets,":[41],"including":[42],"limited":[43],"object":[44],"categories,":[45],"insufficient":[46],"textual":[47],"diversity,":[48],"a":[50,77,93,120,127],"scarcity":[51],"of":[52,99,122,129],"high-quality":[53],"annotations.":[54],"To":[55],"mitigate":[56],"these":[57],"limitations,":[58],"we":[59],"introduce":[60],"GroundingSuite,":[61],"which":[62],"comprises:":[63],"(1)":[64],"an":[65],"automated":[66],"data":[67,146],"annotation":[68,136,147],"framework":[69,137],"leveraging":[70],"multiple":[71],"Vision-Language":[72],"Model":[73],"(VLM)":[74],"agents;":[75],"(2)":[76],"large-scale":[78],"training":[79,104],"dataset":[80,105],"9.56":[82],"million":[83],"diverse":[84],"referring":[85],"expressions":[86],"their":[88],"corresponding":[89],"segmentations;":[90],"(3)":[92],"meticulously":[94],"curated":[95],"evaluation":[96],"benchmark":[97],"consisting":[98],"3,800":[100],"images.":[101],"The":[102],"GroundingSuite":[103,135],"facilitates":[106],"substantial":[107],"performance":[108],"improvements,":[109],"enabling":[110],"models":[111],"trained":[112],"on":[113,124,131],"it":[114],"achieve":[116],"state-of-the-art":[117],"results.":[118],"Specifically,":[119],"cIoU":[121],"68.9":[123],"gRefCOCO":[125],"gIoU":[128],"55.3":[130],"RefCOCOm.":[132],"Moreover,":[133],"demonstrates":[138],"superior":[139],"efficiency":[140],"compared":[141],"current":[144],"leading":[145],"method,":[148],"i.e.,":[149],"$4.5":[150],"\\times$":[151],"faster":[152],"than":[153],"GLaMM.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}