![wildcapture](/sites/default/files/styles/max_325x325/public/2024-07/Dataset2_0.png?itok=slp2kLS1)
![wildcapture](/sites/default/files/styles/max_325x325/public/2024-07/Dataset2_0.png?itok=slp2kLS1)
Architecture and GAN-based training procedure for obtaining a fast neural network which enable better bitrate performances respect to the H.265 codec for the same quality, or better quality at the same bitrate.
Dataset of 4D dynamic sequences of 3D faces with varying facial expressions
d-Simplex classifiers achieve stationary, compatible features, enabling seamless model updates in retrieval systems.
A novel dataset of dynamic sequences of 3D face models, where a combination of synthetic and real identities exhibit an unprecedented variety of 4D facial expressions, with variations that include the classical neutral-apex transition, but generalize to e...
Using fixed classifiers derived from regular polytopes to enhance neural network efficiency and accuracy by generating stationary, maximally-separated feature representations.
Elastic Feature Consolidation (EFC), exploits a tractable second-order approximation of feature drift based on an Empirical Feature Matrix (EFM).
We propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter.
We propose a two-stage learning baseline with a learnable weight scaling layer for reducing the bias caused by long-tailed distribution in LT-CIL and which in turn also improves the performance of conventional CIL due to the limited exemplars.
Synthetic Social Agents (SSA) is intended to be an oversimplification of real social behaviors, yet offers a challenging shift of attention from individual motion to social forces.
Neural network based on an end-to-end trainable working memory, which acts as an external storage where information about each agent can be continuously written, updated and recalled
Image Auto Tagging technology enables automatic assignment of relevant tags or keywords to vast collections of images and videos.