
Classifier Crafting: Turn Your ConvNet into a ZeroShot Learner!
In Zeroshot learning (ZSL), we classify unseen categories using textual...
read it

DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
In this work, we address the problem of learning an ensemble of speciali...
read it

On Fast Leverage Score Sampling and Optimal Learning
Leverage score sampling provides an appealing way to perform approximate...
read it

Explainable Deep Classification Models for Domain Generalization
Conventionally, AI models are thought to trade off explainability for lo...
read it

Constructing fast approximate eigenspaces with application to the fast graph Fourier transforms
We investigate numerically efficient approximations of eigenspaces assoc...
read it

Generative Pseudolabel Refinement for Unsupervised Domain Adaptation
We investigate and characterize the inherent resilience of conditional G...
read it

IntraCamera Supervised Person ReIdentification: A New Benchmark
Existing person reidentification (reid) methods rely mostly on a large...
read it

Cognitive architecture aided by workingmemory for selfsupervised multimodal humans recognition
The ability to recognize human partners is an important social skill to ...
read it

Fast approximation of orthogonal matrices and application to PCA
We study the problem of approximating orthogonal matrices so that their ...
read it

Model Vulnerability to Distributional Shifts over Image Transformation Sets
We are concerned with the vulnerability of computer vision models to dis...
read it

Gaze Estimation for Assisted Living Environments
Effective assisted living environments must be able to perform inference...
read it

Learning Unbiased Representations via Mutual Information Backpropagation
We are interested in learning datadriven representations that can gener...
read it

Crossmodal Speaker Verification and Recognition: A Multilingual Perspective
Recent years have seen a surge in finding association between faces and ...
read it

Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans
In this paper, we tackle the task of automatically analyzing 3D volumetr...
read it

Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
We propose a guided dropout regularizer for deep networks based on the e...
read it

Dirichletbased Gaussian Processes for Largescale Calibrated Classification
In this paper, we study the problem of deriving fast and accurate classi...
read it

A Differential Volumetric Approach to MultiView Photometric Stereo
Highly accurate 3D volumetric reconstruction is still an open research t...
read it

Multibranch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
In this paper, we present an automated approach for segmenting multiple ...
read it

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
Gaussian processes (GP) are a popular Bayesian approach for the optimiza...
read it

Towards Learning How to Properly Play UNO with the iCub Robot
While interacting with another person, our reactions and behavior are mu...
read it

Learning with privileged information via adversarial discriminative modality distillation
Heterogeneous data modalities can provide complementary cues for several...
read it

ATIS + SpiNNaker: a Fully Eventbased Visual Tracking Demonstration
The Asynchronous Timebased Image Sensor (ATIS) and the Spiking Neural N...
read it

MinimalEntropy Correlation Alignment for Unsupervised Deep Domain Adaptation
In this work, we face the problem of unsupervised domain adaptation with...
read it

Invariant components of synergy, redundancy, and unique information among three variables
In a system of three stochastic variables, the Partial Information Decom...
read it

Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Recent works showed that Generative Adversarial Networks (GANs) can be s...
read it

The identity of information: how deterministic dependencies constrain information synergy and redundancy
Understanding how different information sources together transmit inform...
read it

Excitation Backprop for RNNs
Deep models are stateoftheart for many vision tasks including video a...
read it

Are we Done with Object Recognition? The iCub robot's Perspective
We report on an extensive study of the current benefits and limitations ...
read it

Curriculum Dropout
Dropout is a very effective way of regularizing neural networks. Stochas...
read it

Robotic Tactile Perception of Object Properties: A Review
Touch sensing can help robots understand their sur rounding environment...
read it

Optimal Rates for Learning with Nyström Stochastic Gradient Methods
In the setting of nonparametric regression, we propose and study a combi...
read it

Dropout as a LowRank Regularizer for Matrix Factorization
Regularization for matrix factorization (MF) and approximation problems ...
read it

An Analysis of Dropout for Matrix Factorization
Dropout is a simple yet effective algorithm for regularizing neural netw...
read it

Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks
We present a new method to translate videos to commands for robotic mani...
read it

The encoding of proprioceptive inputs in the brain: knowns and unknowns from a robotic perspective
Somatosensory inputs can be grossly divided into tactile (or cutaneous) ...
read it

AffordanceNet: An EndtoEnd Deep Learning Approach for Object Affordance Detection
We propose AffordanceNet, a new deep learning approach to simultaneously...
read it

Recognizing Objects Inthewild: Where Do We Stand?
The ability to recognize objects is an essential skill for a robotic sys...
read it

Quantifying multivariate redundancy with maximum entropy decompositions of mutual information
Williams and Beer (2010) proposed a nonnegative mutual information decom...
read it

Solving ℓ^pnorm regularization with tensor kernels
In this paper, we discuss how a suitable family of tensor kernels can be...
read it

RealTime Pose Estimation for Event Cameras with Stacked Spatial LSTM Networks
We present a new method to estimate the 6DOF pose of the event camera so...
read it

Manifold Constrained LowRank Decomposition
Lowrank decomposition (LRD) is a stateoftheart method for visual dat...
read it

When Kernel Methods meet Feature Learning: LogCovariance Network for Action Recognition from Skeletal Data
Human action recognition from skeletal data is a hot research topic and ...
read it

Convergence of the ForwardBackward Algorithm: Beyond the Worst Case with the Help of Geometry
We provide a comprehensive study of the convergence of forwardbackward ...
read it

A Bridge Between Hyperparameter Optimization and Larningtolearn
We consider a class of a nested optimization problems involving inner an...
read it

Bounds for VectorValued Function Estimation
We present a framework to derive risk bounds for vectorvalued learning ...
read it

Optimal Rates for Multipass Stochastic Gradient Methods
We analyze the learning properties of the stochastic gradient method whe...
read it

Generalization Properties and Implicit Regularization for Multiple Passes SGM
We study the generalization properties of stochastic gradient methods fo...
read it

Generalized support vector regression: duality and tensorkernel representation
In this paper we study the variational problem associated to support vec...
read it

Online semiparametric learning for inverse dynamics modeling
This paper presents a semiparametric algorithm for online learning of a...
read it

Incremental Semiparametric Inverse Dynamics Learning
This paper presents a novel approach for incremental semiparametric inve...
read it
Istituto Italiano di Tecnologia
Istituto Italiano di Tecnologia (IIT) is a research institute that promotes excellence in basic and applied research and fostering Italy's economic development