{"id":"https://openalex.org/W4404987247","doi":"https://doi.org/10.1109/iccv51701.2025.00661","title":"Open-Vocabulary Octree-Graph for 3D Scene Understanding","display_name":"Open-Vocabulary Octree-Graph for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404987247","doi":"https://doi.org/10.1109/iccv51701.2025.00661"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.16253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100414847","display_name":"Zhigang Wang","orcid":"https://orcid.org/0000-0003-1025-4664"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045379790","display_name":"Yifei Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Su","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649746","display_name":"Chenhui Li","orcid":"https://orcid.org/0000-0001-9835-2650"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhui Li","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102688508","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-0953-2236"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019313500","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-2262-1540"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I2800413675","display_name":"Telenor (Norway)","ror":"https://ror.org/02jsp2z03","country_code":"NO","type":"company","lineage":["https://openalex.org/I2800413675"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["TeleAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TeleAI","institution_ids":["https://openalex.org/I2800413675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044934274","display_name":"Bin Zhao","orcid":"https://orcid.org/0000-0003-2461-5299"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhao","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":"7037","last_page":"7047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9873999953269958,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9873999953269958,"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":0.9819999933242798,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9656000137329102,"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/octree","display_name":"Octree","score":0.8945937156677246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781585812568665},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6243554949760437},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5753641128540039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41258448362350464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4104834794998169},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3261953592300415},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2902025580406189},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23534497618675232}],"concepts":[{"id":"https://openalex.org/C141297171","wikidata":"https://www.wikidata.org/wiki/Q1143237","display_name":"Octree","level":2,"score":0.8945937156677246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781585812568665},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6243554949760437},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5753641128540039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41258448362350464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4104834794998169},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3261953592300415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2902025580406189},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23534497618675232},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.16253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16253","pdf_url":"https://arxiv.org/pdf/2411.16253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.16253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.16253","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.16253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16253","pdf_url":"https://arxiv.org/pdf/2411.16253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G766557878","display_name":null,"funder_award_id":"62376222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7755912295","display_name":null,"funder_award_id":"2023QNRC001","funder_id":"https://openalex.org/F4320311778","funder_display_name":"China Association for Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404987247.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2776826689","https://openalex.org/W2145484806","https://openalex.org/W2099745724","https://openalex.org/W2348653124","https://openalex.org/W2089908184","https://openalex.org/W2392270594","https://openalex.org/W2156453104","https://openalex.org/W2773541276","https://openalex.org/W2389430001","https://openalex.org/W1979313280"],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,27,82,105],"scene":[2,78,83],"understanding":[3],"is":[4,34,115,135,173],"indispensable":[5],"for":[6,16,59,80],"embodied":[7],"agents.":[8],"Recent":[9],"works":[10],"leverage":[11],"pretrained":[12],"vision-language":[13],"models":[14],"(VLMs)":[15],"object":[17,67,126],"segmentation":[18],"and":[19,45,65,93,107,120,145,167],"project":[20],"them":[21],"to":[22,25,103,129],"point":[23,32],"clouds":[24],"build":[26],"maps.":[28],"Despite":[29],"progress,":[30],"a":[31,35,76,86,142],"cloud":[33],"set":[36],"of":[37,124,169],"unordered":[38],"coordinates":[39],"that":[40,117],"requires":[41],"substantial":[42],"storage":[43],"space":[44],"does":[46],"not":[47],"directly":[48],"convey":[49],"occupancy":[50,123],"information":[51],"or":[52],"spatial":[53,149],"relation,":[54],"making":[55],"existing":[56],"methods":[57],"inefficient":[58],"downstream":[60],"tasks,":[61],"e.g.,":[62],"path":[63],"planning":[64],"text-based":[66],"retrieval.":[68],"To":[69],"address":[70],"these":[71],"issues,":[72],"we":[73],"propose":[74],"\\textbf{Octree-Graph},":[75],"novel":[77],"representation":[79],"open-vocabulary":[81],"understanding.":[84],"Specifically,":[85],"Chronological":[87],"Group-wise":[88],"Segment":[89],"Merging":[90],"(CGSM)":[91],"strategy":[92],"an":[94,112,125],"Instance":[95],"Feature":[96],"Aggregation":[97],"(IFA)":[98],"algorithm":[99],"are":[100,158],"first":[101],"designed":[102],"get":[104],"instances":[106],"corresponding":[108],"semantic":[109],"features.":[110],"Subsequently,":[111],"adaptive-octree":[113,139],"structure":[114],"developed":[116],"stores":[118],"semantics":[119],"depicts":[121],"the":[122,133,148,165],"adjustably":[127],"according":[128],"its":[130],"shape.":[131],"Finally,":[132],"Octree-Graph":[134],"constructed":[136],"where":[137],"each":[138],"acts":[140],"as":[141],"graph":[143],"node,":[144],"edges":[146],"describe":[147],"relations":[150],"among":[151],"nodes.":[152],"Extensive":[153],"experiments":[154],"on":[155,160],"various":[156],"tasks":[157],"conducted":[159],"several":[161],"widely-used":[162],"datasets,":[163],"demonstrating":[164],"versatility":[166],"effectiveness":[168],"our":[170],"method.":[171],"Code":[172],"available":[174],"\\href{https://github.com/yifeisu/OV-Octree-Graph}{here}.":[175]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}