{"id":"https://openalex.org/W4416510437","doi":"https://doi.org/10.1109/iccv51701.2025.00736","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation","display_name":"Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416510437","doi":"https://doi.org/10.1109/iccv51701.2025.00736"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00736","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23120","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049997329","display_name":"Zhenhua Ning","orcid":"https://orcid.org/0009-0001-4993-7035"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenhua Ning","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038086218","display_name":"Zhuotao Tian","orcid":"https://orcid.org/0000-0003-2698-6923"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuotao Tian","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083443210","display_name":"Shaoshuai Shi","orcid":"https://orcid.org/0000-0003-2558-181X"},"institutions":[{"id":"https://openalex.org/I4210097479","display_name":"Voyager Therapeutics (United States)","ror":"https://ror.org/010cnye54","country_code":"US","type":"company","lineage":["https://openalex.org/I4210097479"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoshuai Shi","raw_affiliation_strings":["Voyager Research, Didi Chuxing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voyager Research, Didi Chuxing","institution_ids":["https://openalex.org/I4210097479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112373191","display_name":"Guangming Lu","orcid":"https://orcid.org/0000-0002-9457-7956"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Lu","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082144617","display_name":"Daojing He","orcid":"https://orcid.org/0000-0002-3820-8128"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daojing He","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078487642","display_name":"Wenjie Pei","orcid":"https://orcid.org/0000-0001-8117-2696"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Pei","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100392380","display_name":"Jiang Li","orcid":"https://orcid.org/0000-0003-0091-6986"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5049997329"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33541132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7851","last_page":"7860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9337999820709229,"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":0.9337999820709229,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.009499999694526196,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.00839999970048666,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/segmentation","display_name":"Segmentation","score":0.7214000225067139},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.6353999972343445},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6172999739646912},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5264000296592712},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5184999704360962},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47760000824928284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42579999566078186},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742999792098999},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7214000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6531000137329102},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00736","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:2506.23120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23120","pdf_url":"https://arxiv.org/pdf/2506.23120","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.23120","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23120","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23120","pdf_url":"https://arxiv.org/pdf/2506.23120","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G7496073333","display_name":null,"funder_award_id":"62372133, 62376074","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":{"Recent":[0],"advances":[1],"in":[2,10,28,105],"point":[3,41,143],"cloud":[4,42,144],"perception":[5,145],"have":[6],"demonstrated":[7],"remarkable":[8],"progress":[9],"scene":[11],"understanding":[12],"through":[13],"vision-language":[14],"alignment":[15],"leveraging":[16],"large":[17],"language":[18],"models":[19],"(LLMs).":[20],"However,":[21],"existing":[22,103],"methods":[23],"may":[24],"still":[25],"encounter":[26],"challenges":[27],"handling":[29],"complex":[30,106],"instructions":[31,91],"that":[32,134,154],"require":[33],"accurate":[34],"spatial":[35,46,79,148],"reasoning,":[36],"even":[37],"if":[38],"the":[39,55,100,135],"3D":[40,111,138,142],"data":[43],"provides":[44],"detailed":[45],"cues":[47],"such":[48],"as":[49,158],"size":[50],"and":[51,121,130,137,151,162],"position":[52],"for":[53,164],"identifying":[54,86],"targets.":[56],"To":[57],"tackle":[58],"this":[59],"issue,":[60],"we":[61,109,152],"propose":[62],"Relevant":[63],"Reasoning":[64],"Segmentation":[65],"(R$^2$S),":[66],"a":[67,113,159],"reasoning-based":[68,114],"segmentation":[69,115],"framework.":[70],"The":[71],"framework":[72],"emulates":[73],"human":[74],"cognitive":[75],"processes":[76],"by":[77,93],"decomposing":[78],"reasoning":[80,107,149],"into":[81],"two":[82],"sequential":[83],"stages:":[84],"first":[85],"relevant":[87],"elements,":[88],"then":[89],"processing":[90],"guided":[92],"their":[94],"associated":[95],"visual":[96],"priors.":[97],"Furthermore,":[98],"acknowledging":[99],"inadequacy":[101],"of":[102],"datasets":[104],"tasks,":[108],"introduce":[110],"ReasonSeg,":[112],"dataset":[116],"comprising":[117],"25,185":[118],"training":[119],"samples":[120,124],"3,966":[122],"validation":[123],"with":[125,146],"precise":[126],"annotations.":[127],"Both":[128],"quantitative":[129],"qualitative":[131],"experiments":[132],"demonstrate":[133],"R$^2$S":[136],"ReasonSeg":[139],"effectively":[140],"endow":[141],"stronger":[147],"capabilities,":[150],"hope":[153],"they":[155],"can":[156],"serve":[157],"new":[160],"baseline":[161],"benchmark":[163],"future":[165],"work.":[166]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}