Zobrazeno 1 - 10
of 292
pro vyhledávání: '"O'Toole, Alice J."'
Autor:
Pal, Basudha, Kannan, Arunkumar, Kathirvel, Ram Prabhakar, O'Toole, Alice J., Chellappa, Rama
Diffusion models have achieved great progress in face generation. However, these models amplify the bias in the generation process, leading to an imbalance in distribution of sensitive attributes such as age, gender and race. This paper proposes a no
Externí odkaz:
http://arxiv.org/abs/2312.14976
Autor:
Myers, Blake A., Jaggernauth, Lucas, Metz, Thomas M., Hill, Matthew Q., Gandi, Veda Nandan, Castillo, Carlos D., O'Toole, Alice J.
Common and important applications of person identification occur at distances and viewpoints in which the face is not visible or is not sufficiently resolved to be useful. We examine body shape as a biometric across distance and viewpoint variation.
Externí odkaz:
http://arxiv.org/abs/2305.19160
Autor:
Jeckeln, Geraldine, Yavuzcan, Selin, Marquis, Kate A., Mehta, Prajay Sandipkumar, Yates, Amy N., Phillips, P. Jonathon, O'Toole, Alice J.
Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. As algorithms continue to improve, it is important to continually assess their race bias relative to
Externí odkaz:
http://arxiv.org/abs/2305.16443
Face identity masking algorithms developed in recent years aim to protect the privacy of people in video recordings. These algorithms are designed to interfere with identification, while preserving information about facial actions. An important chall
Externí odkaz:
http://arxiv.org/abs/2301.08408
Autor:
Parde, Connor J., Strehle, Virginia E., Banerjee, Vivekjyoti, Hu, Ying, Cavazos, Jacqueline G., Castillo, Carlos D., O'Toole, Alice J.
Deep convolutional neural networks (DCNNs) have achieved human-level accuracy in face identification (Phillips et al., 2018), though it is unclear how accurately they discriminate highly-similar faces. Here, humans and a DCNN performed a challenging
Externí odkaz:
http://arxiv.org/abs/2207.05316
Autor:
Mallick, Snipta, Jeckeln, Geraldine, Parde, Connor J., Castillo, Carlos D., O'Toole, Alice J.
Facial morphs created between two identities resemble both of the faces used to create the morph. Consequently, humans and machines are prone to mistake morphs made from two identities for either of the faces used to create the morph. This vulnerabil
Externí odkaz:
http://arxiv.org/abs/2204.12591
Autor:
Russell, Madisen T., Hajdúk, Michal, Springfield, Cassi R., Klein, Hans S., Bass, Emily L., Mittal, Vijay A., Williams, Trevor F., O’Toole, Alice J., Pinkham, Amy E.
Publikováno v:
In Schizophrenia Research: Cognition June 2024 36
Autor:
Jeckeln, Géraldine, Hu, Ying, Cavazos, Jacqueline G., Yates, Amy N., Hahn, Carina A., Tang, Larry, Phillips, P. Jonathon, O'Toole, Alice J.
Measures of face-identification proficiency are essential to ensure accurate and consistent performance by professional forensic face examiners and others who perform face-identification tasks in applied scenarios. Current proficiency tests rely on s
Externí odkaz:
http://arxiv.org/abs/2106.15323
Autor:
Parde, Connor J., Colón, Y. Ivette, Hill, Matthew Q., Castillo, Carlos D., Dhar, Prithviraj, O'Toole, Alice J.
Deep convolutional neural networks (DCNNs) trained for face identification develop representations that generalize over variable images, while retaining subject (e.g., gender) and image (e.g., viewpoint) information. Identity, gender, and viewpoint c
Externí odkaz:
http://arxiv.org/abs/2002.06274
Previous generations of face recognition algorithms differ in accuracy for images of different races (race bias). Here, we present the possible underlying factors (data-driven and scenario modeling) and methodological considerations for assessing rac
Externí odkaz:
http://arxiv.org/abs/1912.07398