{"id":"https://openalex.org/W7131841622","doi":"https://doi.org/10.1109/sii64115.2026.11404599","title":"Grid-Based Marking Prompt Framework for Spatial Understanding in Vision\u2013Language Models","display_name":"Grid-Based Marking Prompt Framework for Spatial Understanding in Vision\u2013Language Models","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131841622","doi":"https://doi.org/10.1109/sii64115.2026.11404599"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5117216277","display_name":"Ryo Terashima","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Terashima","raw_affiliation_strings":["Kyushu Institute of Technology,Fukuoka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Fukuoka,Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075800482","display_name":"Yuga Yano","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuga Yano","raw_affiliation_strings":["Kyushu Institute of Technology,Fukuoka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Fukuoka,Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127234618","display_name":"Koshun Arimura","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koshun Arimura","raw_affiliation_strings":["Kyushu Institute of Technology,Fukuoka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Fukuoka,Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126996591","display_name":"Hakaru Tamukoh","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hakaru Tamukoh","raw_affiliation_strings":["Kyushu Institute of Technology,Fukuoka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Fukuoka,Japan","institution_ids":["https://openalex.org/I207014233"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I207014233"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1593","last_page":"1598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7712000012397766,"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":0.7712000012397766,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.07289999723434448,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.03139999881386757,"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/task","display_name":"Task (project management)","score":0.6100000143051147},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5831999778747559},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.515999972820282},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4869000017642975},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.450300008058548},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.38040000200271606},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3675999939441681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786899983882904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6100000143051147},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515000224113464},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.36649999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2947311533","https://openalex.org/W3099587965","https://openalex.org/W3134399564","https://openalex.org/W4210606756","https://openalex.org/W4294816927","https://openalex.org/W4312424618","https://openalex.org/W4385430559","https://openalex.org/W4389667423","https://openalex.org/W4392775481","https://openalex.org/W4401415110","https://openalex.org/W4401417336","https://openalex.org/W4403918554","https://openalex.org/W4404612908","https://openalex.org/W4407403282","https://openalex.org/W4407403436","https://openalex.org/W4413144805","https://openalex.org/W4413145013","https://openalex.org/W4413156275","https://openalex.org/W4415800665"],"related_works":[],"abstract_inverted_index":{"In":[0,103,124],"this":[1],"study,":[2],"we":[3],"propose":[4],"a":[5,48,110,122,132,145,148,154],"grid-based":[6],"marking":[7],"prompt":[8,83],"framework":[9,19,61,77,128,152,169],"to":[10,28,31,54,115],"enhance":[11],"spatial":[12,33],"understanding":[13],"in":[14,147,158,170],"vision-language":[15],"models":[16,70],"(VLMs).":[17],"The":[18,60,151],"integrates":[20],"object":[21,100,138],"detection,":[22],"background":[23],"masking,":[24],"and":[25,34,92,135,164],"number":[26,52],"overlaying":[27],"enable":[29],"VLMs":[30],"interpret":[32],"contextual":[35],"instructions":[36],"more":[37],"effectively.":[38],"By":[39],"inputting":[40],"numbered":[41],"images":[42,107],"along":[43],"with":[44],"natural":[45],"language":[46],"instructions,":[47],"VLM":[49,146],"selects":[50],"the":[51,55,75,99,117,127,137,162,168],"corresponding":[53],"most":[56],"semantically":[57],"appropriate":[58],"location.":[59],"operates":[62],"without":[63],"requiring":[64],"prior":[65],"information":[66],"such":[67],"as":[68],"3D":[69],"or":[71],"physical":[72],"markers.":[73],"Moreover,":[74],"proposed":[76],"allows":[78],"flexible":[79],"rule":[80],"adaptation":[81],"through":[82],"engineering":[84],"alone,":[85],"providing":[86],"general":[87],"applicability":[88],"across":[89],"various":[90],"objects":[91],"environments.":[93,172],"We":[94],"conducted":[95,136],"two":[96],"experiments":[97],"for":[98],"placement":[101,118,139],"task.":[102],"experiment":[104,125],"1,":[105],"shelf":[106],"captured":[108],"by":[109,144],"service":[111,133],"robot":[112,134],"were":[113],"used":[114],"evaluate":[116],"selection":[119],"accuracy":[120],"of":[121,167],"VLM.":[123],"2,":[126],"was":[129],"implemented":[130],"on":[131],"task":[140],"at":[141],"positions":[142],"selected":[143],"real-world":[149,171],"environment.":[150],"achieved":[153],"high":[155],"success":[156],"rate":[157],"both":[159],"experiments,":[160],"demonstrating":[161],"effectiveness":[163],"practical":[165],"utility":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-28T00:00:00"}