{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:14:56Z","timestamp":1784146496418,"version":"3.55.0"},"reference-count":98,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00730","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7782-7793","source":"Crossref","is-referenced-by-count":1,"title":["TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Mohammadi","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Igor","family":"Gilitschenski","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","author":"Alexey","year":"2016","journal-title":"IEEE TPAMI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref3","article-title":"BEiT: Bert pre-training of image transformers","author":"Bao","year":"2022","journal-title":"ICLR"},{"key":"ref4","author":"Binas","year":"2017","journal-title":"DDD17: End-to-end davis driving dataset"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iscas.2014.6865228"},{"key":"ref6","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref11","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref13","author":"Chen","year":"2020","journal-title":"Improved baselines with momentum contrastive learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01819"},{"key":"ref17","author":"De Tournemire","year":"2020","journal-title":"A large scale eventbased detection dataset for automotive"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00213"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref21","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2022","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref24","article-title":"Masked autoencoders as spatiotemporal learners","author":"Feichtenhofer","year":"2022","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063149"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3008413"},{"key":"ref27","author":"Ge","year":"2021","journal-title":"Yolox: Exceeding yolo series in 2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060707"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00030"},{"key":"ref32","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Self-supervised learning of event-based optical flow with spiking neural networks","author":"Hagenaars","year":"2021","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02190"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref37","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"Henaff","year":"2020","journal-title":"ICML"},{"key":"ref38","article-title":"Autoencoders, minimum description length and helmholtz free energy","author":"Hinton","year":"1993","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00536"},{"key":"ref43","author":"Huang","year":"2024","journal-title":"Data-efficient event camera pre-training via disentangled masked modeling"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594119"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793924"},{"key":"ref46","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref47","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00237"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162962"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341802"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802220"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3378742"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref54","author":"Makhzani","year":"2015","journal-title":"Adversarial autoencoders"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145053"},{"key":"ref57","author":"Van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref58","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00345"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00555"},{"key":"ref62","author":"Peng","year":"2022","journal-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers"},{"key":"ref63","article-title":"Learning to detect objects with a 1 megapixel event camera","author":"Perot","year":"2020","journal-title":"NeurIPS"},{"key":"ref64","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref65","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00398"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2963386"},{"key":"ref69","article-title":"Continuous-time intensity estimation using event cameras","author":"Scheerlinck","year":"2018","journal-title":"ACCV"},{"key":"ref70","article-title":"Convolutional 1stm network: A machine learning approach for precipitation nowcasting","author":"Shi","year":"2015","journal-title":"NeurIPS"},{"key":"ref71","author":"Song","year":"2022","journal-title":"It takes two: Masked appearancemotion modeling for self-supervised video transformer pretraining"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref75","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref76","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","author":"Vincent","year":"2010","journal-title":"JMLR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00994"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref82","author":"Wu","year":"2023","journal-title":"EventCLIP: Adapting clip for event-based object recognition"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01602"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref85","author":"Xie","year":"2021","journal-title":"Self-supervised learning with swin transformers"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref87","author":"Yang","year":"2022","journal-title":"Selfsupervised video representation learning with motion-aware masked autoencoders"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00982"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00982"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_5"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01652"},{"key":"ref93","article-title":"Image bert pre-training with online tokenizer","author":"Zhou","year":"2022","journal-title":"ICLR"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_27"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800793"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00216"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01180"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00556"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444241.pdf?arnumber=11444241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:26Z","timestamp":1777613366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00730","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}