Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Neehar Peri"'
Autor:
Alexandra A. Shaver, Neehar Peri, Remy Mezebish, George Matthew, Alyza Berson, Christopher Gaskins, Gregory P. Davis, Garrett E. Katz, Immanuel Samuel, Matthew J. Reinhard, Michelle E. Costanzo, James A. Reggia, James Purtilo, Rodolphe J. Gentili
Publikováno v:
Augmented Cognition ISBN: 9783031054563
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c00c348f3a44f7b0e010c3800d79768
https://doi.org/10.1007/978-3-031-05457-0_28
https://doi.org/10.1007/978-3-031-05457-0_28
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585679
ECCV (14)
ECCV (14)
In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2818c9374e06c2d9343b617501d78044
https://doi.org/10.1007/978-3-030-58568-6_22
https://doi.org/10.1007/978-3-030-58568-6_22
Autor:
Soheil Feizi, Liam Fowl, John P. Dickerson, Tom Goldstein, Chen Zhu, Neal Gupta, Neehar Peri, W. Ronny Huang
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030664145
ECCV Workshops (1)
ECCV Workshops (1)
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a particular tes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9e94b453ea250bcec567791b31baa70
https://doi.org/10.1007/978-3-030-66415-2_4
https://doi.org/10.1007/978-3-030-66415-2_4
Autor:
Rama Chellappa, Jun-Cheng Chen, Amit Kumar, Sai Saketh Rambhatla, Neehar Peri, Pirazh Khorramshahi
Publikováno v:
ICCV
In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25731e4add571316faeddeccc03a686e
http://arxiv.org/abs/1905.03397
http://arxiv.org/abs/1905.03397