{"id":"https://openalex.org/W6991210175","doi":null,"title":"F\u00f6rb\u00e4ttra spr\u00e5kmodellers f\u00f6rst\u00e5else av 3D-milj\u00f6er genom scendiagram","display_name":"F\u00f6rb\u00e4ttra spr\u00e5kmodellers f\u00f6rst\u00e5else av 3D-milj\u00f6er genom scendiagram","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6991210175"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-360135","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-360135","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1938505/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1938505/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qian, Siyi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qian, Siyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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":0.9951000213623047,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.000699999975040555,"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/large-language-models","display_name":"large language models","score":0.7689999938011169},{"id":"https://openalex.org/keywords/3d-scene-understanding","display_name":"3D scene understanding","score":0.921999990940094},{"id":"https://openalex.org/keywords/scene-graph","display_name":"scene graph","score":0.8650000095367432},{"id":"https://openalex.org/keywords/3d-scene-reconstruction","display_name":"3D scene reconstruction","score":0.8769999742507935},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/llava","display_name":"LLaVA","score":0.9089999794960022},{"id":"https://openalex.org/keywords/gpt","display_name":"GPT","score":0.9110000133514404},{"id":"https://openalex.org/keywords/ai2-thor","display_name":"AI2-THOR","score":0.9179999828338623},{"id":"https://openalex.org/keywords/3d-scene-representation","display_name":"3D scene representation","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7143999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791999936103821},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5271000266075134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5164999961853027},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4821999967098236},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:DiVA.org:kth-360135","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-360135","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1938505/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-360135","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-360135","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1938505/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6991210175.pdf","grobid_xml":"https://content.openalex.org/works/W6991210175.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2913583088","https://openalex.org/W2982399380","https://openalex.org/W2997591391","https://openalex.org/W3030163527","https://openalex.org/W3039448353","https://openalex.org/W4382246105","https://openalex.org/W4392172801"],"related_works":["https://openalex.org/W4386936529","https://openalex.org/W4402427278","https://openalex.org/W4393372075","https://openalex.org/W7166824122","https://openalex.org/W7134042867","https://openalex.org/W4415955476","https://openalex.org/W7133246057","https://openalex.org/W7131898060","https://openalex.org/W4395022832","https://openalex.org/W4405792509"],"abstract_inverted_index":{"In":[0,28,58],"recent":[1],"years,":[2],"large":[3,21,55],"language":[4,22,56,153],"models":[5,154],"have":[6,156],"developed":[7],"a":[8,20,37,157],"strong":[9],"ability":[10,97,111,141],"to":[11,24],"generate":[12],"texts.":[13],"However,":[14],"it":[15],"is":[16],"still":[17],"challenging":[18],"for":[19,174,194],"model":[23],"understand":[25],"3D":[26,42,51,94,118,139],"scenes.":[27],"2023,":[29],"ConceptGraphs":[30,82,99],"pipeline":[31,66,83,100],"was":[32],"proposed.":[33],"It":[34],"can":[35,84,155],"build":[36],"scene":[38,43,52,95,185,206],"graph":[39,186],"as":[40,80],"the":[41,47,50,54,70,81,93,102,108,117,126,133,138,148,167,176,181,184,190,196,201,205],"representation":[44,119],"and":[45,53,68,114,187],"bridge":[46],"gap":[48],"between":[49],"model.":[57],"this":[59,65,73],"thesis":[60],"project,":[61],"we":[62,91,106],"investigate":[63],"how":[64],"works":[67],"evaluate":[69,92,107],"workflow":[71],"of":[72,98,112,132,147],"pipeline.":[74],"The":[75,129,145,169],"evaluation":[76],"contains":[77,183,203],"two":[78,88],"parts":[79],"be":[85,123],"divided":[86],"into":[87],"parts.":[89],"First,":[90],"reconstruction":[96,140],"with":[101,116],"AI2-THOR":[103],"dataset.":[104],"Second,":[105],"spatial":[109],"reasoning":[110],"LLaVA":[113],"GPT":[115],"form":[120],"that":[121,137,152,173],"could":[122],"obtained":[124],"from":[125],"first":[127,134],"part.":[128],"experiment":[130],"results":[131,146,170],"part":[135,150],"show":[136,151,172],"needs":[142],"more":[143],"development.":[144],"second":[149],"better":[158],"performance":[159,178,198],"when":[160,180,200],"there":[161],"are":[162],"not":[163],"many":[164],"objects":[165],"in":[166],"scene.":[168],"also":[171],"LLaVA,":[175],"best":[177,197],"happens":[179,199],"input":[182,202],"image":[188],"at":[189],"same":[191],"time,":[192],"while":[193],"GPT,":[195],"only":[204],"graph.":[207]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
