Search Results for author:
Found 24 papers, 4 papers with code
Learning using privileged information for segmenting tumors on digital mammograms
We repeat the student training procedure by providing the assistance of the teacher model this time.
Simulator-Free Visual Domain Randomization via Video Games
In a more challenging setting, BehAVE manages to improve the zero-shot transferability of foundation models to unseen FPS games (up to 22%) even when trained on a game of a different genre (Minecraft).
Towards General Game Representations: Decomposing Games Pixels into Content and Style
On-screen game footage contains rich contextual information that players process when playing and experiencing a game.
From the Lab to the Wild: Affect Modeling via Privileged Information
Privileged information enables affect models to be trained across multiple modalities available in a lab, and ignore, without significant performance drops, those modalities that are not available when they operate in the wild.
The Invariant Ground Truth of Affect
In particular, we assume that the ground truth of affect can be found in the causal relationships between elicitation, manifestation and annotation that remain \emph{invariant} across tasks and participants.
Supervised Contrastive Learning for Affect Modelling
Affect modeling is viewed, traditionally, as the process of mapping measurable affect manifestations from multiple modalities of user input to affect labels.
Automatic inspection of cultural monuments using deep and tensor-based learning on hyperspectral imagery
In Cultural Heritage, hyperspectral images are commonly used since they provide extended information regarding the optical properties of materials.
Game State Learning via Game Scene Augmentation
Having access to accurate game state information is of utmost importance for any artificial intelligence task including game-playing, testing, player modeling, and procedural content generation.
Revisiting lp-constrained Softmax Loss: A Comprehensive Study
Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large.
Learning Task-Independent Game State Representations from Unlabeled Images
We train an image encoder with three widely used SSL algorithms using solely the raw frames, and then attempt to recover the internal state variables from the learned representations.
RankNEAT: Outperforming Stochastic Gradient Search in Preference Learning Tasks
Stochastic gradient descent (SGD) is a premium optimization method for training neural networks, especially for learning objectively defined labels such as image objects and events.
AffRankNet+: Ranking Affect Using Privileged Information
Many of the affect modelling tasks present an asymmetric distribution of information between training and test time; additional information is given about the training data, which is not available at test time.
Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification
We hereby propose the Rank-R Feedforward Neural Network (FNN), a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters, thereby offering two core advantages compared to typical machine learning methods.
The Pixels and Sounds of Emotion: General-Purpose Representations of Arousal in Games
What if emotion could be captured in a general and subject-agnostic fashion?
Human-Computer Interaction
Space-Time Domain Tensor Neural Networks: An Application on Human Pose Classification
Recent advances in sensing technologies require the design and development of pattern recognition models capable of processing spatiotemporal data efficiently.
Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles
To the best of our knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments.
From Pixels to Affect: A Study on Games and Player Experience
Is it possible to predict the affect of a user just by observing her behavioral interaction through a video?
A Deep Reinforcement Learning Driving Policy for Autonomous Road Vehicles
This work regards our preliminary investigation on the problem of path planning for autonomous vehicles that move on a freeway.
Robotics
Common Mode Patterns for Supervised Tensor Subspace Learning
In this work we propose a method for reducing the dimensionality of tensor objects in a binary classification framework.
Tensor-based Nonlinear Classifier for High-Order Data Analysis
We also introduce a new learning algorithm to train the model, and we evaluate the \textit{Rank}-1 FNN on third-order hyperspectral data.
Tensor-Based Classifiers for Hyperspectral Data Analysis
Then, we introduce learning algorithms to train both the linear and the non-linear classifier in a way to i) to minimize the error over the training samples and ii) the weight coefficients satisfies the {\it rank}-1 canonical decomposition property.
Data-Driven Background Subtraction Algorithm for in-Camera Acceleration in Thermal Imagery
Detection of moving objects in videos is a crucial step towards successful surveillance and monitoring applications.
Deep supervised learning for hyperspectral data classification through convolutional neural networks
Our method exploits a Convolutional Neural Network to encode pixels' spectral and spatial information and a Multi-Layer Perceptron to conduct the classification task.
Variational Inference for Background Subtraction in Infrared Imagery
We propose a Gaussian mixture model for background subtraction in infrared imagery.
