{"id":"https://openalex.org/W7123654354","doi":"https://doi.org/10.1109/mmsp64401.2025.11324169","title":"SpatialGeo: Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion","display_name":"SpatialGeo: Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123654354","doi":"https://doi.org/10.1109/mmsp64401.2025.11324169"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"article","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/A5122972366","display_name":"Jiajie Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajie Guo","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616624","display_name":"Qian Zhu","orcid":"https://orcid.org/0000-0001-7062-8221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingpeng Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003121","display_name":"Jin Zeng","orcid":"https://orcid.org/0000-0002-0180-7733"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zeng","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121194312","display_name":"Xiaolong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Wu","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064989610","display_name":"Changyong H\u00e9","orcid":"https://orcid.org/0000-0002-8438-0631"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyong He","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121662050","display_name":"Weida Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weida Wang","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5122972366"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66364347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8944000005722046,"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":0.8944000005722046,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.02070000022649765,"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":0.005900000222027302,"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/boosting","display_name":"Boosting (machine learning)","score":0.6958000063896179},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6782000064849854},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.6184999942779541},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5702000260353088},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5640000104904175},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5449000000953674},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.48500001430511475},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4388999938964844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098000049591064},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6958000063896179},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6621000170707703},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6184999942779541},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.46050000190734863},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3129831491","https://openalex.org/W4389523832","https://openalex.org/W4400645329","https://openalex.org/W4402727764","https://openalex.org/W4402754023","https://openalex.org/W4403923795","https://openalex.org/W4404295407","https://openalex.org/W4404356490","https://openalex.org/W4405079066","https://openalex.org/W4406857575","https://openalex.org/W4409129939","https://openalex.org/W4413144646","https://openalex.org/W4413145529","https://openalex.org/W4413926275","https://openalex.org/W4415800665"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1,21],"language":[2,12,22],"models":[3,23,168],"(MLLMs)":[4],"have":[5],"achieved":[6],"significant":[7],"progress":[8],"in":[9,40,92,125,162,173],"image":[10],"and":[11,36,58,65,138],"tasks":[13],"due":[14],"to":[15,34,99,106,144],"the":[16,67,78,84,88,110,122,126,151,160],"strong":[17],"reasoning":[18,32,164],"capability":[19,70],"of":[20,56,71,87],"(LLMs).":[24],"Nevertheless,":[25],"most":[26,93],"MLLMs":[27,95],"suffer":[28],"from":[29,83,113],"limited":[30],"spatial":[31,38,68,79,123,163],"ability":[33],"interpret":[35],"infer":[37],"arrangements":[39],"three-dimensional":[41],"space.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,74],"propose":[47],"a":[48,118],"novel":[49],"vision":[50,89],"encoder":[51,90],"based":[52],"on":[53,150],"hierarchical":[54,119],"fusion":[55],"geometry":[57,111],"semantics":[59],"features,":[60],"generating":[61],"spatial-aware":[62],"visual":[63],"embedding":[64,86],"boosting":[66],"grounding":[69],"MLLMs.":[72],"Specifically,":[73],"first":[75],"unveil":[76],"that":[77,157],"ambiguity":[80],"shortcoming":[81],"stems":[82],"lossy":[85],"utilized":[91],"existing":[94],"(e.g.,":[96],"CLIP),":[97],"restricted":[98],"instance-level":[100],"semantic":[101],"features.":[102],"This":[103],"motivates":[104],"us":[105],"complement":[107],"CLIP":[108,152],"with":[109,140,175],"features":[112],"vision-only":[114],"self-supervised":[115],"learning":[116],"via":[117,187],"adapter,":[120],"enhancing":[121,166],"awareness":[124],"proposed":[127],"SpatialGeo.":[128],"The":[129,182],"network":[130],"is":[131,185],"efficiently":[132],"trained":[133],"using":[134],"pretrained":[135],"LLaVA":[136],"model":[137],"optimized":[139],"random":[141],"feature":[142],"dropping":[143],"avoid":[145],"trivial":[146],"solutions":[147],"relying":[148],"solely":[149],"encoder.":[153],"Experimental":[154],"results":[155],"show":[156],"SpatialGeo":[158],"improves":[159],"accuracy":[161],"tasks,":[165],"state-of-the-art":[167],"by":[169],"at":[170],"least":[171],"8.0%":[172],"SpatialRGPT-Bench":[174],"\u223c50%":[176],"less":[177],"memory":[178],"cost":[179],"during":[180],"inference.":[181],"source":[183],"code":[184],"available":[186],"https://ricky-plus.github.io/SpatialGeoPages/.":[188]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}