{"id":"https://openalex.org/W7160300068","doi":"https://doi.org/10.1109/wacv61042.2026.00745","title":"HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning","display_name":"HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160300068","doi":"https://doi.org/10.1109/wacv61042.2026.00745"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5135388399","display_name":"Xiaoyun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyun Hu","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100985461","display_name":"Xiaohan Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Yan","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115694726","display_name":"Hongtao Wang","orcid":"https://orcid.org/0009-0005-9539-865X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135411205","display_name":"Gang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wei","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135326137","display_name":"Zhicheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Wang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5199363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7719","last_page":"7729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4090000092983246,"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":0.4090000092983246,"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":0.14740000665187836,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09700000286102295,"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/process","display_name":"Process (computing)","score":0.3124000132083893},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.27950000762939453},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2791999876499176},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27549999952316284},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2680000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5889999866485596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W1995875735","https://openalex.org/W2150884987","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2970641574","https://openalex.org/W3107521863","https://openalex.org/W3156636935","https://openalex.org/W3172806051","https://openalex.org/W3182910454","https://openalex.org/W4226376247","https://openalex.org/W4312270234","https://openalex.org/W4385245566","https://openalex.org/W4386075660","https://openalex.org/W4389518760","https://openalex.org/W4390873101","https://openalex.org/W4390874439","https://openalex.org/W4402704629","https://openalex.org/W4402713111","https://openalex.org/W4402716272","https://openalex.org/W4402727764","https://openalex.org/W4402961820","https://openalex.org/W4403069390","https://openalex.org/W4403778769","https://openalex.org/W4403791765","https://openalex.org/W4404007470","https://openalex.org/W4405248620","https://openalex.org/W4405595839","https://openalex.org/W4409367459","https://openalex.org/W4413145624","https://openalex.org/W4413146040","https://openalex.org/W4413158055","https://openalex.org/W4413918687","https://openalex.org/W4413925051","https://openalex.org/W4414281281","https://openalex.org/W7133193597","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3],"achieved":[4],"remarkable":[5],"success":[6],"in":[7],"various":[8],"domains.":[9],"However,":[10],"their":[11],"application":[12],"to":[13,53,80],"3D":[14,21,55],"scene":[15,98,127],"understanding":[16],"remains":[17],"largely":[18],"underexplored.":[19],"Existing":[20],"VLMs":[22],"predominantly":[23],"focus":[24],"on":[25,114,125,139],"object-level":[26,131],"tasks":[27],"and":[28,78,130],"often":[29],"emphasize":[30],"instance-centric":[31],"representations":[32],"within":[33],"a":[34,83,108,140],"scene,":[35],"lacking":[36],"holistic":[37],"scene-level":[38,88],"descriptions.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,100],"propose":[44],"an":[45],"automated":[46],"annotation":[47],"framework":[48,96],"that":[49,119],"leverages":[50],"multi-view":[51],"images":[52],"partition":[54],"scenes":[56],"into":[57],"localized":[58],"point":[59],"cloud":[60],"sub-regions,":[61],"which":[62],"are":[63],"then":[64],"enriched":[65],"with":[66],"precise":[67],"semantic":[68],"information-all":[69],"without":[70],"any":[71],"manual":[72],"intervention.":[73],"We":[74,116],"processed":[75],"ScanNet":[76],"v2":[77],"ScanNet++":[79],"construct":[81],"SceneCap,":[82],"large-scale":[84],"dataset":[85],"designed":[86],"for":[87,97,154],"description.":[89],"To":[90],"demonstrate":[91,118],"the":[92,152],"benefits":[93],"of":[94,137],"our":[95],"understanding,":[99],"introduce":[101],"Natural":[102],"Interactive":[103],"Universal":[104],"Multimodal":[105],"Observer,":[106],"NIUMO-LLM,":[107],"lightweight":[109],"yet":[110],"high-performing":[111],"model":[112],"training":[113,138],"SceneCap.":[115],"further":[117],"NIUMO-LLM":[120],"achieves":[121],"state-of-the-art":[122],"(SOTA)":[123],"performance":[124],"both":[126],"description":[128],"benchmarks":[129],"tasks,":[132],"requiring":[133],"only":[134],"12":[135],"hours":[136],"single":[141],"NVIDIA":[142],"A800":[143],"GPU.":[144],"This":[145],"design":[146],"significantly":[147],"reduces":[148],"computational":[149],"demands,":[150],"lowering":[151],"barrier":[153],"MLLM-related":[155],"research.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}