{"id":"https://openalex.org/W4417161975","doi":"https://doi.org/10.1109/iccv51701.2025.00730","title":"TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras","display_name":"TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417161975","doi":"https://doi.org/10.1109/iccv51701.2025.00730"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00730","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011593040","display_name":"Mohammad Mohammadi","orcid":"https://orcid.org/0000-0002-7761-2692"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad Mohammadi","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076788807","display_name":"Ziyi Wu","orcid":"https://orcid.org/0000-0001-6207-381X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ziyi Wu","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078356081","display_name":"Igor Gilitschenski","orcid":"https://orcid.org/0000-0001-6426-365X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Igor Gilitschenski","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48066391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7782","last_page":"7793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9254999756813049,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9254999756813049,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.00839999970048666,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/feed-forward","display_name":"Feed forward","score":0.5752000212669373},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5123999714851379},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.44350001215934753},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4309000074863434},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3903000056743622},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38600000739097595},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7371000051498413},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.44350001215934753},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3124000132083893},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00730","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:2508.00913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00913","pdf_url":"https://arxiv.org/pdf/2508.00913","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.00913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00913","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.00913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00913","pdf_url":"https://arxiv.org/pdf/2508.00913","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-term":[0],"temporal":[1,76],"information":[2,77,141],"is":[3,96,103,147],"crucial":[4],"for":[5,54,91,98],"event-based":[6,55],"perception":[7],"tasks,":[8,178],"as":[9,101],"raw":[10,67],"events":[11,68,133],"only":[12],"encode":[13],"pixel":[14],"brightness":[15],"changes.":[16],"Recent":[17],"works":[18],"show":[19],"that":[20],"when":[21,37],"trained":[22],"from":[23],"scratch,":[24],"recurrent":[25,47,99],"models":[26,32,43,65],"achieve":[27],"better":[28],"results":[29,175],"than":[30],"feedforward":[31,42,64],"in":[33,176],"these":[34],"tasks.":[35],"However,":[36],"leveraging":[38],"self-supervised":[39,50,87],"pre-trained":[40],"weights,":[41],"can":[44],"outperform":[45],"their":[46],"counterparts.":[48],"Current":[49],"learning":[51,92],"(SSL)":[52],"methods":[53],"pre-training":[56,88],"largely":[57],"mimic":[58],"RGB":[59],"image-based":[60],"approaches.":[61],"They":[62],"pre-train":[63],"on":[66],"within":[69],"a":[70,86,122,128],"short":[71],"time":[72],"interval,":[73],"ignoring":[74],"the":[75,104,116,143,161],"of":[78,168],"events.":[79,169],"In":[80],"this":[81,157],"work,":[82],"we":[83],"introduce":[84],"TESPEC,":[85],"framework":[89,106],"tailored":[90],"spatio-temporal":[93],"information.":[94],"TESPEC":[95,114],"well-suited":[97],"models,":[100],"it":[102],"first":[105],"to":[107,131,149,163],"leverage":[108],"long":[109],"event":[110],"sequences":[111],"during":[112],"pre-training.":[113],"employs":[115],"masked":[117],"image":[118],"modeling":[119],"paradigm":[120],"with":[121],"new":[123],"reconstruction":[124],"target.":[125],"We":[126],"design":[127],"novel":[129],"method":[130],"accumulate":[132],"into":[134],"pseudo":[135],"grayscale":[136],"videos":[137],"containing":[138],"high-level":[139],"semantic":[140,182],"about":[142,165],"underlying":[144],"scene,":[145],"which":[146],"robust":[148],"sensor":[150],"noise":[151],"and":[152,184],"reduces":[153],"motion":[154],"blur.":[155],"Reconstructing":[156],"target":[158],"thus":[159],"requires":[160],"model":[162],"reason":[164],"long-term":[166],"history":[167],"Extensive":[170],"experiments":[171],"demonstrate":[172],"our":[173],"state-of-the-art":[174],"downstream":[177],"including":[179],"object":[180],"detection,":[181],"segmentation,":[183],"monocular":[185],"depth":[186],"estimation.":[187],"Project":[188],"webpage:":[189],"https://mhdmohammadi.github.io/TESPEC_webpage.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}