{"id":"https://openalex.org/W4415536269","doi":"https://doi.org/10.1145/3746027.3758163","title":"A Matter of Time: Revealing the Structure of Time in Vision-Language Models","display_name":"A Matter of Time: Revealing the Structure of Time in Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536269","doi":"https://doi.org/10.1145/3746027.3758163"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758163","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758163","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120131179","display_name":"Nidham Tekaya","orcid":null},"institutions":[{"id":"https://openalex.org/I25485817","display_name":"University of Applied Sciences St P\u00f6lten","ror":"https://ror.org/039a2re55","country_code":"AT","type":"education","lineage":["https://openalex.org/I25485817"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Nidham Tekaya","raw_affiliation_strings":["St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria and TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0003-8679-4082","affiliations":[{"raw_affiliation_string":"St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria and TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I25485817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061106600","display_name":"Manuela Waldner","orcid":"https://orcid.org/0000-0003-1387-5132"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Manuela Waldner","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1387-5132","affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060926433","display_name":"Matthias Zeppelzauer","orcid":"https://orcid.org/0000-0003-0413-4746"},"institutions":[{"id":"https://openalex.org/I25485817","display_name":"University of Applied Sciences St P\u00f6lten","ror":"https://ror.org/039a2re55","country_code":"AT","type":"education","lineage":["https://openalex.org/I25485817"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Matthias Zeppelzauer","raw_affiliation_strings":["St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0413-4746","affiliations":[{"raw_affiliation_string":"St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria","institution_ids":["https://openalex.org/I25485817"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32392992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12371","last_page":"12380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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":0.9983999729156494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9731000065803528,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9458000063896179,"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/embedding","display_name":"Embedding","score":0.7490000128746033},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.7307999730110168},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.551800012588501},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5120999813079834},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.460999995470047},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4392000138759613},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7490000128746033},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.7307999730110168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6237999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5961999893188477},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758163","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.19559","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19559","pdf_url":"https://arxiv.org/pdf/2510.19559","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758163","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3491986705","display_name":null,"funder_award_id":"10.55776/DFH37","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2017329135","https://openalex.org/W2044329284","https://openalex.org/W2295208133","https://openalex.org/W2889326414","https://openalex.org/W3000465807","https://openalex.org/W3035002246","https://openalex.org/W3126605730","https://openalex.org/W3156892778","https://openalex.org/W4288055192","https://openalex.org/W4297461125","https://openalex.org/W4306820534","https://openalex.org/W4327519267","https://openalex.org/W4361194507","https://openalex.org/W4366850565","https://openalex.org/W4377832121","https://openalex.org/W4379259759","https://openalex.org/W4386065512","https://openalex.org/W4386071707","https://openalex.org/W4387561339","https://openalex.org/W4390873312","https://openalex.org/W4390874242","https://openalex.org/W4391632217","https://openalex.org/W4392964660","https://openalex.org/W4394591113","https://openalex.org/W4402671141","https://openalex.org/W4402706236","https://openalex.org/W4402727079","https://openalex.org/W4402775923","https://openalex.org/W4411549762","https://openalex.org/W4413147859","https://openalex.org/W6912494966"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"such":[4],"as":[5],"CLIP":[6],"have":[7],"gained":[8],"popularity":[9],"for":[10],"their":[11,33,45],"generalizable":[12],"and":[13,67,117,121,146],"expressive":[14],"multimodal":[15],"representations.":[16],"By":[17],"leveraging":[18],"large-scale":[19],"training":[20,34],"data":[21,147],"with":[22,63],"diverse":[23],"textual":[24],"metadata,":[25],"VLMs":[26,73],"acquire":[27],"open-vocabulary":[28],"capabilities,":[29],"solving":[30],"tasks":[31],"beyond":[32],"scope.":[35],"This":[36],"paper":[37],"investigates":[38],"the":[39,69,92,110],"temporal":[40,64,82,124],"awareness":[41],"of":[42,59,71],"VLMs,":[43],"assessing":[44],"ability":[46],"to":[47,103,132,136],"position":[48],"visual":[49],"content":[50],"in":[51,91],"time.":[52],"We":[53],"introduce":[54],"TIME10k,":[55],"a":[56,75,87,137],"benchmark":[57],"dataset":[58],"over":[60],"10,000":[61],"images":[62],"ground":[65],"truth,":[66],"evaluate":[68],"time-awareness":[70],"37":[72],"by":[74],"novel":[76],"methodology.":[77],"Our":[78,127],"investigation":[79],"reveals":[80],"that":[81],"information":[83],"is":[84],"structured":[85],"along":[86],"low-dimensional,":[88],"non-linear":[89],"manifold":[90],"VLM":[93],"embedding":[94,111],"space.":[95,112],"Based":[96],"on":[97],"this":[98],"insight,":[99],"we":[100],"propose":[101],"methods":[102],"derive":[104],"an":[105],"explicit":[106],"``timeline''":[107],"representation":[108],"from":[109],"These":[113],"representations":[114],"model":[115],"time":[116],"its":[118],"chronological":[119],"progression":[120],"thereby":[122],"facilitate":[123],"reasoning":[125],"tasks.":[126],"timeline":[128],"approaches":[129],"achieve":[130],"competitive":[131],"superior":[133],"accuracy":[134],"compared":[135],"prompt-based":[138],"baseline":[139],"while":[140],"being":[141],"computationally":[142],"efficient.":[143],"All":[144],"code":[145],"are":[148],"available":[149],"at":[150],"https://tekayanidham.github.io/timeline-page/.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}