no code implementations • 15 Jun 2021 • David McNeely-White, Ben Sattelberg, Nathaniel Blanchard, Ross Beveridge
When instead evaluating embeddings generated from two CNNs, where one CNN's embeddings are mapped with a linear transformation, the mean true accept rate drops to 0. 95 using the same verification paradigm.
no code implementations • 30 Nov 2020 • Ben Sattelberg, Renzo Cavalieri, Michael Kirby, Chris Peterson, Ross Beveridge
The weights in the neural network determine a decomposition of the input space into convex polytopes and on each of these polytopes the network can be described by a single affine mapping.
no code implementations • 5 Oct 2020 • David McNeely-White, Benjamin Sattelberg, Nathaniel Blanchard, Ross Beveridge
When image embeddings generated by one CNN are transformed into embeddings corresponding to the feature space of a second CNN trained on the same task, their respective image classification or face verification performance is largely preserved.
no code implementations • 11 Apr 2020 • Ameni Trabelsi, Mohamed Chaabane, Nathaniel Blanchard, Ross Beveridge
Our approach is composed of 2 main components: the first component classifies the objects in the input image and proposes an initial 6D pose estimate through a multi-task, CNN-based encoder/multi-decoder module.
1 code implementation • 10 Apr 2020 • Mohamed Chaabane, Lionel Gueguen, Ameni Trabelsi, Ross Beveridge, Stephen O'Hara
We also show that the end-to-end system performance is further improved via joint-training of the constituent models.
no code implementations • 20 Oct 2019 • Mohamed Chaabane, Ameni Trabelsi, Nathaniel Blanchard, Ross Beveridge
Our end-to-end model consists of two stages: the first stage is an encoder/decoder network that learns to predict future video frames.
no code implementations • CVPR 2018 • Pradyumna Narayana, Ross Beveridge, Bruce A. Draper
Gestures are a common form of human communication and important for human computer interfaces (HCI).