{"id":"https://openalex.org/W4416799976","doi":"https://doi.org/10.1109/snpd65828.2025.11254066","title":"Enhancing Spatial Reasoning in Multimodal Vision-Language Models via Depth-Aware Feature Integration","display_name":"Enhancing Spatial Reasoning in Multimodal Vision-Language Models via Depth-Aware Feature Integration","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4416799976","doi":"https://doi.org/10.1109/snpd65828.2025.11254066"},"language":null,"primary_location":{"id":"doi:10.1109/snpd65828.2025.11254066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd65828.2025.11254066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 29th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","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/A5010407841","display_name":"Hiroo Tsuji","orcid":null},"institutions":[{"id":"https://openalex.org/I121165721","display_name":"Otemon Gakuin University","ror":"https://ror.org/009mysd22","country_code":"JP","type":"education","lineage":["https://openalex.org/I121165721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroo Tsuji","raw_affiliation_strings":["Otemon Gakuin University,Department of Information Engineering,Ibaraki,Japan"],"affiliations":[{"raw_affiliation_string":"Otemon Gakuin University,Department of Information Engineering,Ibaraki,Japan","institution_ids":["https://openalex.org/I121165721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010407841"],"corresponding_institution_ids":["https://openalex.org/I121165721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4072556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"472","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872000217437744,"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":0.9872000217437744,"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":0.0017999999690800905,"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":0.0010000000474974513,"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":0.5885999798774719},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5735999941825867},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5356000065803528},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4912000000476837},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.4478999972343445},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4422000050544739},{"id":"https://openalex.org/keywords/chart","display_name":"Chart","score":0.4287000000476837},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7080000042915344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snpd65828.2025.11254066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd65828.2025.11254066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 29th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2561715562","https://openalex.org/W2963518342","https://openalex.org/W4381802186","https://openalex.org/W4389520792","https://openalex.org/W4389667009","https://openalex.org/W4402716288","https://openalex.org/W4415800665"],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1,87],"such":[2],"as":[3],"Contrastive":[4],"Language-Image":[5],"Pre-training":[6],"(CLIP)":[7],"excel":[8],"at":[9],"aligning":[10],"images":[11],"and":[12,40,51,68,76],"text,":[13],"yet":[14],"they":[15],"still":[16],"struggle":[17],"to":[18,31],"reason":[19],"about":[20],"spatial":[21,91],"relationships":[22],"within":[23],"a":[24,28,35,81],"scene.":[25],"We":[26],"present":[27],"lightweight":[29],"extension":[30],"CLIP":[32],"that":[33],"injects":[34],"depth":[36,41],"modality,":[37],"fusing":[38],"RGB":[39],"features":[42],"while":[43,110],"preserving":[44],"the":[45,94,98,112],"model\u2019s":[46],"pre-trained":[47],"visual-textual":[48],"knowledge.":[49],"Trained":[50],"evaluated":[52],"on":[53],"dedicated":[54],"spatial-reasoning":[55],"benchmarks,":[56],"our":[57],"depth-enhanced":[58],"architecture":[59],"yields":[60],"substantial":[61],"accuracy":[62,114],"gains":[63],"over":[64],"an":[65],"RGB-only":[66],"baseline":[67],"produces":[69],"more":[70],"human-like":[71],"judgments":[72],"of":[73],"relative":[74],"position":[75],"distance.":[77],"These":[78],"findings":[79],"chart":[80],"clear":[82],"path":[83],"from":[84,118],"2-D":[85],"image-language":[86],"toward":[88],"true":[89],"3-D":[90],"understanding.":[92],"Crucially,":[93],"compact":[95],"design":[96],"retains":[97],"rich":[99],"semantics":[100],"learned":[101],"during":[102],"CLIP\u2019S":[103],"large-scale":[104],"pre-training,":[105],"enabling":[106],"markedly":[107],"faster":[108],"convergence":[109],"matching":[111],"final":[113],"achieved":[115],"by":[116],"training":[117],"scratch.":[119]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}