{"id":"https://openalex.org/W7133122939","doi":"https://doi.org/10.3390/computers15030145","title":"SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding","display_name":"SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133122939","doi":"https://doi.org/10.3390/computers15030145"},"language":"en","primary_location":{"id":"doi:10.3390/computers15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15030145","pdf_url":"https://www.mdpi.com/2073-431X/15/3/145/pdf?version=1772334230","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/15/3/145/pdf?version=1772334230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127744423","display_name":"Jinyuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyuan Li","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen 361000, China"],"raw_orcid":"https://orcid.org/0009-0000-1875-7712","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen 361000, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123996793","display_name":"Yundong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yundong Wu","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen 361000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen 361000, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121986795","display_name":"Tiancai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166335","display_name":"Xiamen Tobacco Industry (China)","ror":"https://ror.org/05t1nkw30","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210166335"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiancai Huang","raw_affiliation_strings":["Xiamen Taqu Information Technology Co., Ltd., Xiamen 361000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Taqu Information Technology Co., Ltd., Xiamen 361000, China","institution_ids":["https://openalex.org/I4210166335","https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041661823","display_name":"Mengyun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengyun Cao","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen 361000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen 361000, China","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041661823","https://openalex.org/A5121986795"],"corresponding_institution_ids":["https://openalex.org/I161346416","https://openalex.org/I4210166335","https://openalex.org/I75867142"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24689253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"3","first_page":"145","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.36160001158714294,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.36160001158714294,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.357699990272522,"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/T12290","display_name":"Human Motion and Animation","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6765999794006348},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5910999774932861},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5257999897003174},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.511900007724762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4763999879360199},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.475600004196167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4702000021934509},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4401000142097473},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.42559999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392999768257141},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6765999794006348},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088000297546387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15030145","pdf_url":"https://www.mdpi.com/2073-431X/15/3/145/pdf?version=1772334230","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3b56100e80094a5ab8b7689df2ebcde5","is_oa":true,"landing_page_url":"https://doaj.org/article/3b56100e80094a5ab8b7689df2ebcde5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 15, Iss 3, p 145 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15030145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15030145","pdf_url":"https://www.mdpi.com/2073-431X/15/3/145/pdf?version=1772334230","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5466049909591675,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1779093446","display_name":null,"funder_award_id":"2023J01799","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G2331034857","display_name":"\u9762\u5411\u65e0\u4eba\u6267\u6cd5\u8239\u7684\u591a\u6a21\u6001\u6df1\u5ea6\u7279\u5f81\u53d8\u6362\u6d77\u9762\u76ee\u6807\u68c0\u6d4b\u65b9\u6cd5","funder_award_id":"2022J01819","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G2721776513","display_name":"\u57fa\u4e8eCT \u5f71\u50cf\u7684\u6025\u6027\u8111\u6897\u6b7b\u75c5\u7076\u5feb\u901f\u8bed\u4e49\u5206\u5272\u65b9\u6cd5","funder_award_id":"2022J011394","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G2892541708","display_name":"\u8de8\u89c6\u89d2\u591a\u6a21\u6001\u6570\u636e\u878d\u5408\u7684\u5927\u573a\u666f\u8bed\u4e49\u4e09\u7ef4\u91cd\u5efa\u65b9\u6cd5","funder_award_id":"2022J02045","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3458291489","display_name":null,"funder_award_id":"2022J01337","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3525545207","display_name":"\u9762\u5411\u591a\u6587\u6863\u6458\u8981\u7684\u6587\u672c\u6838\u5fc3\u8bed\u4e49\u663e\u5f0f\u8868\u793a\u65b9\u6cd5\u7814\u7a76","funder_award_id":"2022J05157","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G4052947816","display_name":null,"funder_award_id":"42371457","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7477423354","display_name":null,"funder_award_id":"2023J01801","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G7891469171","display_name":null,"funder_award_id":"2023J01799","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8359015589","display_name":null,"funder_award_id":"42371343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873737750","display_name":null,"funder_award_id":"42301468","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"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133122939.pdf","grobid_xml":"https://content.openalex.org/works/W7133122939.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,17,78,107],"visual":[1,154],"grounding":[2],"is":[3,138],"a":[4,65,110,132,207,218,228],"fundamental":[5],"task":[6],"for":[7,77],"human\u2013machine":[8],"interaction,":[9],"aiming":[10],"to":[11,45,53,117,140,200],"localize":[12],"specific":[13],"objects":[14],"in":[15,213,231],"complex":[16],"point":[18,155],"clouds":[19],"based":[20],"on":[21,33,187,216,221,234],"natural":[22],"language":[23],"descriptions.":[24],"Despite":[25],"recent":[26],"advancements,":[27],"existing":[28],"Transformer-based":[29],"architectures":[30],"often":[31],"rely":[32],"absolute":[34],"position":[35],"embeddings":[36,152],"and":[37,51,73,123,153,189,227],"heuristic":[38],"query":[39],"initialization,":[40],"which":[41,95],"lack":[42],"the":[43,89,102,115,128,147,169,180,194,201,222],"capacity":[44],"capture":[46,119],"fine-grained":[47],"relative":[48,120],"spatial":[49,121],"dependencies":[50],"fail":[52],"effectively":[54],"filter":[55],"out":[56],"scene":[57],"clutter.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,87],"propose":[63,88],"SESQ,":[64],"novel":[66],"framework":[67],"that":[68,168],"synergizes":[69],"Spatially":[70,91],"Aware":[71,92],"Encoding":[72],"Semantically":[74],"Guided":[75],"Querying":[76],"grounding.":[79],"Our":[80],"approach":[81],"introduces":[82],"two":[83],"key":[84],"innovations.":[85],"First,":[86],"Rotary":[90,97],"Encoder":[93],"(RSAE),":[94],"incorporates":[96],"Position":[98],"Embeddings":[99],"(RoPE)":[100],"into":[101,109],"self-attention":[103],"layers.":[104],"By":[105,158],"transforming":[106],"coordinates":[108],"rotary":[111],"representation,":[112],"RSAE":[113],"enables":[114],"model":[116],"inherently":[118],"distances":[122],"maintains":[124],"geometric":[125],"consistency":[126],"throughout":[127],"encoding":[129],"stage.":[130],"Second,":[131],"Semantic":[133],"Query":[134],"Initialization":[135],"(SQI)":[136],"module":[137],"designed":[139],"initialize":[141],"object":[142,176],"queries":[143],"by":[144],"explicitly":[145],"computing":[146],"cross-modal":[148],"similarity":[149],"between":[150],"textual":[151],"cloud":[156],"features.":[157],"replacing":[159],"traditional":[160],"heuristic-based":[161],"selection":[162],"with":[163],"semantic-aware":[164],"alignment,":[165],"SQI":[166],"ensures":[167],"decoding":[170],"process":[171],"originates":[172],"from":[173],"contextually":[174],"relevant":[175],"candidates,":[177],"significantly":[178],"reducing":[179],"impact":[181],"of":[182,196,211],"task-irrelevant":[183],"distractors.":[184],"Extensive":[185],"experiments":[186],"ScanRefer":[188],"ReferIt3D":[190],"(Nr3D/Sr3D)":[191],"benchmarks":[192],"demonstrate":[193],"effectiveness":[195],"our":[197,204],"framework.":[198],"Compared":[199],"baseline":[202],"EDA,":[203],"method":[205],"achieves":[206],"significant":[208],"performance":[209],"gain":[210],"2.68%":[212],"overall":[214,232],"Acc@0.5":[215],"ScanRefer,":[217],"4.9%":[219],"improvement":[220],"challenging":[223],"Nr3D":[224],"\u201cHard\u201d":[225],"subset,":[226],"1.1%":[229],"increase":[230],"Acc@0.25":[233],"Sr3D.":[235]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-02T00:00:00"}