{"id":"https://openalex.org/W4417102205","doi":"https://doi.org/10.1109/iccv51701.2025.00805","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","display_name":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417102205","doi":"https://doi.org/10.1109/iccv51701.2025.00805"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00805","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100681325","display_name":"Shijie Zhou","orcid":"https://orcid.org/0000-0001-6411-7222"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shijie Zhou","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102736683","display_name":"Alexander Vilesov","orcid":"https://orcid.org/0000-0001-6197-734X"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Vilesov","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101181260","display_name":"Xuehai He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xuehai He","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026082030","display_name":"Ziyu Wan","orcid":"https://orcid.org/0000-0003-2421-3484"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ziyu Wan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuwang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuwang Zhang","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120718288","display_name":"Aditya Nagachandra","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Nagachandra","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111772447","display_name":"Di Chang","orcid":"https://orcid.org/0009-0002-0281-8896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Chang","raw_affiliation_strings":["USC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364591","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-7016-9288"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328100","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-2605-5504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Eric Wang","raw_affiliation_strings":["UCSC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039720020","display_name":"Achuta Kadambi","orcid":"https://orcid.org/0000-0002-2444-2503"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Achuta Kadambi","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81771959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8600","last_page":"8612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9915000200271606,"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":0.9915000200271606,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","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/perspective","display_name":"Perspective (graphical)","score":0.6638000011444092},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6377999782562256},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5974000096321106},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44769999384880066},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473000288009644},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6377999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212000250816345},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00805","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:2508.02095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02095","pdf_url":"https://arxiv.org/pdf/2508.02095","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.02095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.02095","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.02095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02095","pdf_url":"https://arxiv.org/pdf/2508.02095","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"language":[1],"models":[2],"(VLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"capabilities":[7,63],"in":[8,18,44,111,150],"integrating":[9,122],"linguistic":[10],"and":[11,26,32,71,82,87,96,126,142,165,174],"visual":[12,124,176],"reasoning":[13,62],"but":[14],"remain":[15],"fundamentally":[16],"limited":[17],"understanding":[19,40],"dynamic":[20,38,179],"spatiotemporal":[21,61,144,152],"interactions.":[22],"Humans":[23],"effortlessly":[24],"track":[25],"reason":[27],"about":[28],"object":[29],"movements,":[30],"rotations,":[31],"perspective":[33,85],"shifts-abilities":[34],"essential":[35],"for":[36,178],"robust":[37],"real-world":[39,70],"yet":[41],"notably":[42],"lacking":[43],"current":[45],"VLMs.":[46,65],"In":[47],"this":[48],"paper,":[49],"we":[50,99],"introduce":[51],"VLM4D,":[52],"the":[53,60,169],"first":[54],"benchmark":[55,67],"specifically":[56],"designed":[57],"to":[58,105,157],"evaluate":[59],"of":[64,93],"Our":[66,154],"comprises":[68],"diverse":[69],"synthetic":[72],"videos":[73],"accompanied":[74],"by":[75],"carefully":[76],"curated":[77],"question-answer":[78],"pairs":[79],"emphasizing":[80],"translational":[81],"rotational":[83],"motions,":[84],"awareness,":[86],"motion":[88],"continuity.":[89],"Through":[90],"comprehensive":[91],"evaluations":[92],"state-of-the-art":[94],"open":[95],"closed-source":[97],"VLMs,":[98],"identify":[100],"significant":[101],"performance":[102],"gaps":[103],"compared":[104],"human":[106],"baselines,":[107],"highlighting":[108],"fundamental":[109],"deficiencies":[110],"existing":[112],"models.":[113],"Extensive":[114],"analysis":[115],"reveals":[116],"that":[117],"VLMs":[118],"struggle":[119],"particularly":[120],"with":[121],"multiple":[123],"cues":[125],"maintaining":[127],"temporal":[128,166],"coherence.":[129],"We":[130],"further":[131],"explore":[132],"promising":[133],"directions,":[134],"such":[135],"as":[136],"leveraging":[137],"4D":[138],"feature":[139],"field":[140],"reconstruction":[141],"targeted":[143],"supervised":[145],"fine-tuning,":[146],"demonstrating":[147],"their":[148],"effectiveness":[149],"enhancing":[151],"comprehension.":[153],"work":[155],"aims":[156],"encourage":[158],"deeper":[159],"exploration":[160],"into":[161],"improving":[162],"VLMs'":[163],"spatial":[164],"grounding,":[167],"paving":[168],"way":[170],"towards":[171],"more":[172],"capable":[173],"reliable":[175],"intelligence":[177],"environments.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}