{"id":"https://openalex.org/W7164820212","doi":"https://doi.org/10.1145/3805622.3810869","title":"TAVEN: Task-driven Adaptive Viewpoint Exploration for Training-Free 3D Spatial Reasoning and Understanding","display_name":"TAVEN: Task-driven Adaptive Viewpoint Exploration for Training-Free 3D Spatial Reasoning and Understanding","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164820212","doi":"https://doi.org/10.1145/3805622.3810869"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810869","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810869","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138633878","display_name":"Shuyi Jiang","orcid":"https://orcid.org/0009-0009-0953-4088"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuyi Jiang","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-0953-4088","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832227","display_name":"Zhihao Yuan","orcid":"https://orcid.org/0000-0003-3100-1252"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Yuan","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3100-1252","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101887026","display_name":"Na Zhao","orcid":"https://orcid.org/0000-0003-2329-7014"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Na Zhao","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2329-7014","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93532828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"911","last_page":"920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9437999725341797,"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":0.9437999725341797,"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":0.006899999920278788,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.005400000140070915,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6460999846458435},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6459000110626221},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5612999796867371},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5027999877929688},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43369999527931213},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4262999892234802},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4223000109195709},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949000000953674},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6460999846458435},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607200026512146},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810869","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810869","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.40810850262641907}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2137792123","https://openalex.org/W2410664773","https://openalex.org/W2594519801","https://openalex.org/W2904904022","https://openalex.org/W2964339842","https://openalex.org/W2964345792","https://openalex.org/W2988715931","https://openalex.org/W3107521863","https://openalex.org/W3130367234","https://openalex.org/W3133833192","https://openalex.org/W3182910454","https://openalex.org/W4225832925","https://openalex.org/W4226376247","https://openalex.org/W4385318467","https://openalex.org/W4386075660","https://openalex.org/W4389474301","https://openalex.org/W4401416853","https://openalex.org/W4402702986","https://openalex.org/W4402713111","https://openalex.org/W4402716272","https://openalex.org/W4402716423","https://openalex.org/W4402754162","https://openalex.org/W4402776116","https://openalex.org/W4409366493","https://openalex.org/W4413147672","https://openalex.org/W4413156282","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133223072","https://openalex.org/W7133246057"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"and":[1,19,40,109,132],"reasoning":[2],"over":[3],"3D":[4,32,88,158],"scenes":[5],"from":[6],"natural":[7],"language":[8],"queries":[9,102],"is":[10],"essential":[11],"for":[12,83,116],"intuitive":[13],"human-machine":[14],"interaction":[15],"in":[16,38],"robotics,":[17],"navigation,":[18],"mixed":[20],"reality.":[21],"While":[22],"existing":[23],"VLM-based":[24],"methods":[25],"address":[26],"this":[27],"task":[28,152],"by":[29],"training":[30],"on":[31,59,106,144],"data,":[33],"they":[34],"face":[35],"significant":[36],"challenges":[37],"scalability":[39],"adaptability":[41],"due":[42],"to":[43,99,128,138],"the":[44],"limited":[45],"availability":[46],"of":[47,87],"such":[48],"data.":[49],"Training-free":[50],"approaches":[51],"offer":[52],"a":[53,75],"promising":[54],"alternative":[55],"but":[56],"often":[57],"depend":[58],"fixed":[60],"camera":[61],"paths,":[62],"coarse":[63],"view":[64],"sampling,":[65],"or":[66],"preprocessed":[67],"inputs,":[68],"limiting":[69],"effective":[70],"reasoning.":[71],"We":[72],"propose":[73],"TAVEN,":[74],"training-free":[76],"framework":[77],"that":[78],"leverages":[79],"MLLM":[80],"(i.e.,":[81],"GPT)":[82],"adaptive,":[84],"task-driven":[85],"exploration":[86,145],"scenes.":[89],"TAVEN":[90,154],"features:":[91],"1)":[92],"Chain-of-Thought":[93],"Query":[94],"Decomposition":[95],"with":[96,125,151],"Dual-Focus":[97],"Reasoning":[98],"break":[100],"down":[101],"into":[103],"sub-tasks":[104],"focused":[105],"relevant":[107,119],"entities":[108],"goals;":[110],"2)":[111],"Global":[112],"Memory-Based":[113],"Dual-Level":[114],"Retrieval":[115],"retrieving":[117],"contextually":[118],"views;":[120],"3)":[121],"Progressive":[122],"View":[123,136],"Adjustment":[124],"Tri-Criteria":[126],"Evaluation":[127],"iteratively":[129],"refine":[130],"viewpoints;":[131],"4)":[133],"Trajectory":[134],"Aware":[135],"Rectification":[137],"suggest":[139],"improved":[140],"(rectified)":[141],"views":[142],"based":[143],"history.":[146],"By":[147],"integrating":[148],"visual":[149],"feedback":[150],"semantics,":[153],"enables":[155],"zero-shot,":[156],"goal-oriented":[157],"reasoning,":[159],"moving":[160],"beyond":[161],"passive":[162],"perception":[163],"toward":[164],"intelligent":[165],"spatial":[166],"understanding.":[167]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}
