Search Results for author:
Found 62 papers, 18 papers with code
Leveraging Acoustic Images for Effective Self-Supervised Audio Representation Learning
However, since 2D planar arrays are cumbersome and not as widespread as ordinary microphones, we propose that the richer information content of acoustic images can be distilled, through a self-supervised learning scheme, into more powerful audio and visual feature representations.
Anticipating Next Active Objects for Egocentric Videos
This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place.
Unsupervised Domain Adaptation for Video Transformers in Action Recognition
On the other hand, the performance of a model in action recognition is heavily affected by domain shift.
From Biased Data to Unbiased Models: a Meta-Learning Approach
It is well known that large deep architectures are powerful models when adequately trained, but may exhibit undesirable behavior leading to confident incorrect predictions, even when evaluated on slightly different test examples.
Compact CNN Structure Learning by Knowledge Distillation
The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices.
Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation
On the contrary, a pre-trained source model is always considered to be available, even though performing poorly on target due to the well-known domain shift problem.
Learning without Seeing nor Knowing: Towards Open Zero-Shot Learning
We formalize OZSL as the problem of recognizing seen and unseen classes (as in GZSL) while also rejecting instances from unknown categories, for which neither visual data nor class embeddings are provided.
Transductive Zero-Shot Learning by Decoupled Feature Generation
In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training.
A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled Illumination
This paper presents a novel setup for automatic visual inspection of cracks in ceramic tile as well as studies the effect of various classifiers and height-varying illumination conditions for this task.
DSLib: An open source library for the dominant set clustering method
This package provides an implementation of the original DS clustering algorithm since no code has been officially released yet, together with a still growing collection of methods and variants related to it.
The Visual Social Distancing Problem
One of the main and most effective measures to contain the recent viral outbreak is the maintenance of the so-called Social Distancing (SD).
Complex-Object Visual Inspection via Multiple Lighting Configurations
The design of an automatic visual inspection system is usually performed in two stages.
Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans
We aim at digitally unwrapping the mummy and identify different segments such as body, bandages and jewelry.
Explainable Deep Classification Models for Domain Generalization
Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision.
Learning Unbiased Representations via Mutual Information Backpropagation
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data.
Intra-Camera Supervised Person Re-Identification
Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data.
Generative Pseudo-label Refinement for Unsupervised Domain Adaptation
We exploit this finding in an iterative procedure where a generative model and a classifier are jointly trained: in turn, the generator allows to sample cleaner data from the target distribution, and the classifier allows to associate better labels to target samples, progressively refining target pseudo-labels.
DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
In this work, we address the problem of learning an ensemble of specialist networks using multimodal data, while considering the realistic and challenging scenario of possible missing modalities at test time.
Aggregation Signature for Small Object Tracking
In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift.
Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI
This paper presents a simple and effective generalization method for magnetic resonance imaging (MRI) segmentation when data is collected from multiple MRI scanning sites and as a consequence is affected by (site-)domain shifts.
Intra-Camera Supervised Person Re-Identification: A New Benchmark
Existing person re-identification (re-id) methods rely mostly on a large set of inter-camera identity labelled training data, requiring a tedious data collection and annotation process therefore leading to poor scalability in practical re-id applications.
Unsupervised Domain-Adaptive Person Re-identification Based on Attributes
Training person re-identification (ReID) algorithms under the supervision of such attributes have proven to be effective in extracting local features which are important for ReID.
Domain Adaptation
Domain Adaptive Person Re-Identification
+2
Audio-Visual Model Distillation Using Acoustic Images
In this paper, we investigate how to learn rich and robust feature representations for audio classification from visual data and acoustic images, a novel audio data modality.
Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets
We are concerned with the vulnerability of computer vision models to distributional shifts.
Cross-modal Learning by Hallucinating Missing Modalities in RGB-D Vision
We report state-of-the-art or comparable results on video action recognition on the largest multimodal dataset available for this task, the NTU RGB+D, as well as on the UWA3DII and Northwestern-UCLA.
Guided Zoom: Questioning Network Evidence for Fine-grained Classification
We propose Guided Zoom, an approach that utilizes spatial grounding of a model's decision to make more informed predictions.
Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
Our method is based on a deep end-to-end 2D convolutional neural network (CNN) for slice-based segmentation of 3D volumetric data.
Learning with privileged information via adversarial discriminative modality distillation
This raises the challenge of how to extract information from multimodal data in the training stage, in a form that can be exploited at test time, considering limitations such as noisy or missing modalities.
Modality Distillation with Multiple Stream Networks for Action Recognition
Particularly, we consider the case of learning representations from depth and RGB videos, while relying on RGB data only at test time.
Generalizing to Unseen Domains via Adversarial Data Augmentation
Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model.
Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
In this work, we utilize the evidence at each neuron to determine the probability of dropout, rather than dropping out neurons uniformly at random as in standard dropout.
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines
Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition.
Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains.
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers for the target samples.
Excitation Backprop for RNNs
Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions.
Dropout as a Low-Rank Regularizer for Matrix Factorization
Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways.
An Analysis of Dropout for Matrix Factorization
While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization.
Summarization and Classification of Wearable Camera Streams by Learning the Distributions Over Deep Features of Out-Of-Sample Image Sequences
In particular, we use constrained Markov walks over a counting grid for modeling image sequences, which not only yield good latent representations, but allow for excellent classification with only a handful of labeled training examples of the new scenes or objects, a scenario typical in lifelogging applications.
A Compact Kernel Approximation for 3D Action Recognition
In this work we reduce such complexity to be linear by proposing a novel and explicit feature map to approximate the kernel function.
Manifold Constrained Low-Rank Decomposition
Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling.
When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data
Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors.
What Will I Do Next? The Intention from Motion Experiment
In this paper, we bridge cognitive and computer vision studies, by demonstrating the effectiveness of video-based approaches for the prediction of human intentions.
Unsupervised Adaptive Re-identification in Open World Dynamic Camera Networks
Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may be temporarily inserted into an existing system to get additional information.
Correlation Alignment by Riemannian Metric for Domain Adaptation
Domain adaptation techniques address the problem of reducing the sensitivity of machine learning methods to the so-called domain shift, namely the difference between source (training) and target (test) data distributions.
Curriculum Dropout
This induces an adaptive regularization scheme that smoothly increases the difficulty of the optimization problem.
Modeling Retinal Ganglion Cell Population Activity with Restricted Boltzmann Machines
The idea was to figure out if binary latent states encode the regularities associated to different visual stimuli, as modes in the joint distribution.
Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds.
Emotion-Based Crowd Representation for Abnormality Detection
We aim at publishing the dataset with the article, to be used as a benchmark for the communities.
Active Regression with Adaptive Huber Loss
This paper addresses the scalar regression problem through a novel solution to exactly optimize the Huber loss in a general semi-supervised setting, which combines multi-view learning and manifold regularization.
Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features, in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds.
Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach
In this paper, we address the new problem of the prediction of human intents.
Revisiting Human Action Recognition: Personalization vs. Generalization
In particular, considering that each human action in the datasets is performed several times by different subjects, we were able to precisely quantify the effect of inter- and intra-subject variability, so as to figure out the impact of several learning approaches in terms of classification performance.
Kernelized Covariance for Action Recognition
In this paper we aim at increasing the descriptive power of the covariance matrix, limited in capturing linear mutual dependencies between variables only.
Action Recognition with Image Based CNN Features
Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model.
Learning With Dataset Bias in Latent Subcategory Models
However, previous work has highlighted the possible danger of simply training a model from the combined datasets, due to the presence of bias.
Sparse Representation Classification With Manifold Constraints Transfer
The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems.
3D Pose from Detections
We present a novel method to infer, in closed-form, a general 3D spatial occupancy and orientation of a collection of rigid objects given 2D image detections from a sequence of images.
Log-Hilbert-Schmidt metric between positive definite operators on Hilbert spaces
This paper introduces a novel mathematical and computational framework, namely {\it Log-Hilbert-Schmidt metric} between positive definite operators on a Hilbert space.
Audio Surveillance: a Systematic Review
Despite surveillance systems are becoming increasingly ubiquitous in our living environment, automated surveillance, currently based on video sensory modality and machine intelligence, lacks most of the time the robustness and reliability required in several real applications.
A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) framework for the problem of learning an unknown functional dependency between a structured input space and a structured output space.
Structural epitome: a way to summarize one’s visual experience
In order to study the properties of total visual input in humans, a single subject wore a camera for two weeks capturing, on average, an image every 20 seconds (www. research. microsoft. com/~jojic/aihs).
Free energy score space
Score functions induced by generative models extract fixed-dimension feature vectors from different-length data observations by subsuming the process of data generation, projecting them in highly informative spaces called score spaces.
