{"id":"https://openalex.org/W4413145659","doi":"https://doi.org/10.1109/cvpr52734.2025.00841","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","display_name":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145659","doi":"https://doi.org/10.1109/cvpr52734.2025.00841"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5044238657","display_name":"Duo Zheng","orcid":"https://orcid.org/0000-0003-1180-6176"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Duo Zheng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052557101","display_name":"Shijia Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijia Huang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406725","display_name":"Liwei Wang","orcid":"https://orcid.org/0000-0003-3264-1294"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwei Wang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044238657"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":13.197,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.98941091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8995","last_page":"9006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9994999766349792,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.760577380657196},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6038802862167358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5530282258987427},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4967987835407257},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4685177803039551},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3981061577796936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760577380657196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6038802862167358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530282258987427},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4967987835407257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4685177803039551},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3981061577796936},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,56,66],"Multimodal":[4],"Large":[5],"Language":[6],"Models":[7],"(MLLMs)":[8],"has":[9],"significantly":[10],"impacted":[11],"various":[12],"multimodal":[13],"tasks.":[14],"However,":[15],"these":[16,113],"models":[17],"face":[18],"challenges":[19],"in":[20,76,84],"tasks":[21],"that":[22,149],"require":[23],"spatial":[24,123],"understanding":[25,159],"within":[26],"3D":[27,57,78,97,102,109,157],"environments.":[28],"Efforts":[29],"to":[30,137],"enhance":[31],"MLLMs,":[32],"such":[33],"as":[34,104],"incorporating":[35,108],"point":[36],"cloud":[37],"features,":[38],"have":[39,130],"been":[40],"made,":[41],"yet":[42],"a":[43,89,132],"considerable":[44],"gap":[45],"remains":[46],"between":[47,141],"the":[48,53,64,139],"models\u2019":[49],"learned":[50],"representations":[51,120],"and":[52,107,144,166],"inherent":[54],"complexity":[55],"scenes.":[58],"This":[59],"discrepancy":[60],"largely":[61],"stems":[62],"from":[63],"training":[65],"MLLMs":[67],"on":[68,155],"predominantly":[69],"2D":[70],"data,":[71],"which":[72],"restricts":[73],"their":[74],"effectiveness":[75],"comprehending":[77],"spaces.":[79],"To":[80],"address":[81],"this":[82,85],"issue,":[83],"paper,":[86],"we":[87,129],"propose":[88],"novel":[90],"generalist":[91],"model,":[92],"i.e.,":[93],"Video-3D":[94,116],"LLM,":[95],"for":[96],"scene":[98,158],"understanding.":[99],"By":[100],"treating":[101],"scenes":[103],"dynamic":[105],"videos":[106],"position":[110],"encoding":[111],"into":[112],"representations,":[114],"our":[115,150],"LLM":[117],"aligns":[118],"video":[119],"with":[121],"real-world":[122],"contexts":[124],"more":[125],"accurately.":[126],"In":[127],"addition,":[128],"implemented":[131],"maximum":[133],"coverage":[134],"sampling":[135],"technique":[136],"optimize":[138],"trade-off":[140],"computational":[142],"cost":[143],"performance.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"model":[151],"achieves":[152],"state-of-the-art":[153],"performance":[154],"several":[156],"benchmarks,":[160],"including":[161],"ScanRefer,":[162],"Multi3DRefer,":[163],"Scan2Cap,":[164],"ScanQA,":[165],"SQA3D.":[167],"Our":[168],"code":[169],"is":[170],"available":[171],"at":[172],"https://github.com/LaVi-Lab/Video-3D-LLM.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}