Ego4D:Around the World in 3,000 Hours of Egocentric Video

Autor: Grauman, Kristen, Wray, Michael, Fragomeni, Adriano, Munro, Jonathan P N, Price, Will, Arbelaez, Pablo, Crandall, David, Damen, Dima, Farinella, Giovanni Maria, Ghanem, Bernard, Jawahar, C.V., Kitani, Kris, Oliva, Aude, Park, Hyun Soo, Rehg, James M., Sato, Yoichi, Shou, Mike Zheng, Torrallba, Antonio, Malik, Jitendra

Publikováno v: Grauman, K, Wray, M, Fragomeni, A, Munro, J P N, Price, W, Arbelaez, P, Crandall, D, Damen, D, Farinella, G M, Ghanem, B, Jawahar, C V, Kitani, K, Oliva, A, Park, H S, Rehg, J M, Sato, Y, Shou, M Z, Torrallba, A & Malik, J 2022, Ego4D : Around the World in 3,000 Hours of Egocentric Video . in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Proceedings. IEEE Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers (IEEE), pp. 18973-18990, Computer Vision and Pattern Recognition (CVPR), United States, 19/06/22 . https://doi.org/10.48550/arXiv.2110.07058, https://doi.org/10.1109/CVPR52688.2022.01842

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily- life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2642::5b01fb1e5115c48c8d07d22bf99cd1f3
https://research-information.bris.ac.uk/ws/files/345991967/2110.07058.pdf