Zobrazeno 1 - 10
of 1 513
pro vyhledávání: '"King, Michael P."'
Autor:
Wu, Haiyu, Tian, Sicong, Bhatta, Aman, Gutierrez, Jacob, Bezold, Grace, Argueta, Genesis, Ricanek Jr., Karl, King, Michael C., Bowyer, Kevin W.
Face Recognition models are commonly trained with web-scraped datasets containing millions of images and evaluated on test sets emphasizing pose, age and mixed attributes. With train and test sets both assembled from web-scraped images, it is critica
Externí odkaz:
http://arxiv.org/abs/2405.15965
The Singular Value Decomposition (SVD) of linear functions facilitates the calculation of their 2-induced norm and row and null spaces, hallmarks of linear control theory. In this work, we present a function representation that, similar to SVD, provi
Externí odkaz:
http://arxiv.org/abs/2404.00112
Autor:
Carreira, João, King, Michael, Pătrăucean, Viorica, Gokay, Dilara, Ionescu, Cătălin, Yang, Yi, Zoran, Daniel, Heyward, Joseph, Doersch, Carl, Aytar, Yusuf, Damen, Dima, Zisserman, Andrew
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling. This poses great challenges given the high correlation between consecutive v
Externí odkaz:
http://arxiv.org/abs/2312.00598
Most studies to date that have examined demographic variations in face recognition accuracy have analyzed 1-to-1 matching accuracy, using images that could be described as "government ID quality". This paper analyzes the accuracy of 1-to-many facial
Externí odkaz:
http://arxiv.org/abs/2309.04447
As virtual and physical identity grow increasingly intertwined, the importance of privacy and security in the online sphere becomes paramount. In recent years, multiple news stories have emerged of private companies scraping web content and doing res
Externí odkaz:
http://arxiv.org/abs/2305.06307
Autor:
Pangelinan, Gabriella, Krishnapriya, K. S., Albiero, Vitor, Bezold, Grace, Zhang, Kai, Vangara, Kushal, King, Michael C., Bowyer, Kevin W.
In recent years, media reports have called out bias and racism in face recognition technology. We review experimental results exploring several speculated causes for asymmetric cross-demographic performance. We consider accuracy differences as repres
Externí odkaz:
http://arxiv.org/abs/2304.07175
Autor:
Wu, Haiyu, Bezold, Grace, Günther, Manuel, Boult, Terrance, King, Michael C., Bowyer, Kevin W.
We report the first systematic analysis of the experimental foundations of facial attribute classification. Two annotators independently assigning attribute values shows that only 12 of 40 common attributes are assigned values with >= 95% consistency
Externí odkaz:
http://arxiv.org/abs/2210.07356
In this work, we develop a neural network-based method to convert a noisy motion signal generated from segmenting rebinned list-mode cardiac SPECT images, to that of a high-quality surrogate signal, such as those seen from external motion tracking sy
Externí odkaz:
http://arxiv.org/abs/2208.01034
It is broadly accepted that there is a "gender gap" in face recognition accuracy, with females having higher false match and false non-match rates. However, relatively little is known about the cause(s) of this gender gap. Even the recent NIST report
Externí odkaz:
http://arxiv.org/abs/2206.04867
We explore varying face recognition accuracy across demographic groups as a phenomenon partly caused by differences in face illumination. We observe that for a common operational scenario with controlled image acquisition, there is a large difference
Externí odkaz:
http://arxiv.org/abs/2206.01881