{"id":"https://openalex.org/W4416799350","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249082","title":"VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation","display_name":"VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799350","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249082"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5040714552","display_name":"An Thi Minh Dao","orcid":"https://orcid.org/0000-0002-1942-3009"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Dao Gia Tuan Dao","raw_affiliation_strings":["Menlo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Menlo Research","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091815053","display_name":"Norapat Buppodom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norapat Buppodom","raw_affiliation_strings":["Menlo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Menlo Research","institution_ids":["https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33054922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1464","last_page":"1469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7773000001907349,"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":0.7773000001907349,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.05339999869465828,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.033799998462200165,"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/voxel","display_name":"Voxel","score":0.8733000159263611},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6668999791145325},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.605400025844574},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.4611999988555908},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4081000089645386},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.8733000159263611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7311000227928162},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":1,"referenced_works":["https://openalex.org/W1920022804"],"related_works":[],"abstract_inverted_index":{"Comprehending":[0],"3D":[1,22,57,133],"environments":[2],"is":[3],"vital":[4],"for":[5,131],"intelligent":[6],"systems":[7],"in":[8],"domains":[9],"like":[10],"robotics":[11],"and":[12,48,88,107],"autonomous":[13],"navigation.":[14],"Voxel":[15],"grids":[16],"offer":[17],"a":[18,34,38,70,96],"structured":[19],"representation":[20],"of":[21,54,95,127],"space,":[23],"but":[24],"extracting":[25],"high-level":[26],"semantic":[27,112,134],"meaning":[28],"remains":[29],"challenging.":[30],"This":[31,119],"paper":[32],"proposes":[33],"novel":[35],"approach":[36],"utilizing":[37],"Vision-Language":[39],"Model":[40],"(VLM)":[41],"to":[42,78,102,123],"extract":[43],"\u201cvoxel":[44],"semantics\u201d-object":[45],"identity,":[46],"color,":[47],"location-from":[49],"voxel":[50,63,138],"data.":[51],"Critically,":[52],"instead":[53],"employing":[55],"complex":[56],"networks,":[58],"our":[59],"method":[60],"processes":[61],"the":[62,74,92,116,125],"space":[64],"by":[65,115],"systematically":[66],"slicing":[67],"it":[68],"along":[69],"primary":[71],"axis":[72],"(e.g.,":[73],"Z":[75],"-axis,":[76],"analogous":[77],"CT":[79],"scan":[80],"slices).":[81],"These":[82],"2D":[83,129],"slices":[84,106],"are":[85],"then":[86],"formatted":[87],"sequentially":[89],"fed":[90],"into":[91],"image":[93],"encoder":[94],"standard":[97],"VLM.":[98],"The":[99],"model":[100],"learns":[101],"aggregate":[103],"information":[104],"across":[105],"correlate":[108],"spatial":[109],"patterns":[110],"with":[111],"concepts":[113],"provided":[114],"language":[117],"component.":[118],"slice-based":[120],"strategy":[121],"aims":[122],"leverage":[124],"power":[126],"pre-trained":[128],"VLMs":[130],"efficient":[132],"understanding":[135],"directly":[136],"from":[137],"representations.":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}