research
∙
04/10/2022
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
Driver observation models are rarely deployed under perfect conditions. ...
share
research
∙
01/02/2021
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models
Beyond assigning the correct class, an activity recognition model should...
research
∙
04/25/2020
Detective: An Attentive Recurrent Model for Sparse Object Detection
In this work, we present Detective - an attentive object detector that i...
research
∙
11/14/2018
Rice-Marlin Codes: Tiny and Efficient Variable-to-Fixed Codes
Marlin is a Variable-to-Fixed (VF) codec optimized for high decoding spe...
research
∙
10/11/2018
Taming the Cross Entropy Loss
We present the Tamed Cross Entropy (TCE) loss function, a robust derivat...
research
∙
11/22/2016