Search Results for author:
Found 60 papers, 15 papers with code
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks.
Ranked #34 on
Image Classification
on MNIST
Efficient moving point handling for incremental 3D manifold reconstruction
From the 3D Delaunay triangulation of these points, state-of-the-art algorithms build a manifold rough model of the scene.
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features.
Ranked #18 on
Semantic Segmentation
on CamVid
Incremental Reconstruction of Urban Environments by Edge-Points Delaunay Triangulation
Urban reconstruction from a video captured by a surveying vehicle constitutes a core module of automated mapping.
Automatic 3D Reconstruction of Manifold Meshes via Delaunay Triangulation and Mesh Sweeping
In this paper we propose a new approach to incrementally initialize a manifold surface for automatic 3D reconstruction from images.
Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking?
Recently, sparse representation based visual tracking methods have attracted increasing attention in the computer vision community.
Robust Moving Objects Detection in Lidar Data Exploiting Visual Cues
Detecting moving objects in dynamic scenes from sequences of lidar scans is an important task in object tracking, mapping, localization, and navigation.
Multi-View Stereo with Single-View Semantic Mesh Refinement
In this paper we propose a novel method to refine both the geometry and the semantic labeling of a given mesh.
Mesh-based 3D Textured Urban Mapping
In the era of autonomous driving, urban mapping represents a core step to let vehicles interact with the urban context.
Multi-View Stereo 3D Edge Reconstruction
This paper presents a novel method for the reconstruction of 3D edges in multi-view stereo scenarios.
Predicting the Next Best View for 3D Mesh Refinement
Finding the best poses to capture part of the scene is one of the most challenging topic that goes under the name of Next Best View.
Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras
Event-based cameras, also known as neuromorphic cameras, are bioinspired sensors able to perceive changes in the scene at high frequency with low power consumption.
ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation
We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time.
Attention Mechanisms for Object Recognition with Event-Based Cameras
Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events.
A Data-driven Prior on Facet Orientation for Semantic Mesh Labeling
Mesh labeling is the key problem of classifying the facets of a 3D mesh with a label among a set of possible ones.
Dense 3D Visual Mapping via Semantic Simplification
Dense 3D visual mapping estimates as many as possible pixel depths, for each image.
TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo
One of the most successful approaches in Multi-View Stereo estimates a depth map and a normal map for each view via PatchMatch-based optimization and fuses them into a consistent 3D points cloud.
Mesh-based Camera Pairs Selection and Occlusion-Aware Masking for Mesh Refinement
Many Multi-View-Stereo algorithms extract a 3D mesh model of a scene, after fusing depth maps into a volumetric representation of the space.
Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics
Indeed, we assess the validity of our novel framework both in the context of perfect information, i. e., known object model, and in the partial information context, i. e., inferring task oriented metrics from vision, underlining advantages and limitations of both situations.
A Differentiable Recurrent Surface for Asynchronous Event-Based Data
Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes.
Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background.
Identification of Probability weighted ARX models with arbitrary domains
Hybrid system identification is a key tool to achieve reliable models of Cyber-Physical Systems from data.
Estimation of Switched Markov Polynomial NARX models
This work targets the identification of a class of models for hybrid dynamical systems characterized by nonlinear autoregressive exogenous (NARX) components, with finite-dimensional polynomial expansions, and by a Markovian switching mechanism.
Facetwise Mesh Refinement for Multi-View Stereo
The refinement step is applied for each facet using only the camera pair selected.
Spatial Temporal Transformer Network for Skeleton-based Action Recognition
Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background.
Probabilistic electric load forecasting through Bayesian Mixture Density Networks
Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids.
DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events".
Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*
Recently, the trend of incorporating differentiable algorithms into deep learning architectures arose in machine learning research, as the fusion of neural layers and algorithmic layers has been beneficial for handling combinatorial data, such as shortest paths on graphs.
Improving Multi-View Stereo via Super-Resolution
Today, Multi-View Stereo techniques are able to reconstruct robust and detailed 3D models, especially when starting from high-resolution images.
Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications
Algebraic Low-rank (LR) channel estimation exploits space-time channel sparsity through the computation of position-dependent MIMO channel eigenmodes leveraging recurrent training vehicle passages in the coverage cell.
SGDE: Secure Generative Data Exchange for Cross-Silo Federated Learning
In this context, federated learning is one of the most influential frameworks for privacy-preserving distributed machine learning, achieving astounding results in many natural language processing and computer vision tasks.
Patchwise Sparse Dictionary Learning from pre-trained Neural Network Activation Maps for Anomaly Detection in Images
In this work, we investigate a methodology to perform anomaly detection and localization on images.
E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications.
E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications.
Object Structural Points Representation for Graph-based Semantic Monocular Localization and Mapping
In this paper, we propose the use of an efficient representation, based on structural points, for the geometry of objects to be used as landmarks in a monocular semantic SLAM system based on the pose-graph formulation.
On the utility and protection of optimization with differential privacy and classic regularization techniques
According to the literature, this approach has proven to be a successful defence against several models' privacy attacks, but its downside is a substantial degradation of the models' performance.
POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
With its sequential model-based optimization strategy, Progressive Neural Architecture Search (PNAS) represents a possible step forward to face this resources issue.
IC3D: Image-Conditioned 3D Diffusion for Shape Generation
To address this limitation and enhance image-guided 3D DDPMs with augmented 3D understanding, we introduce CISP (Contrastive Image-Shape Pre-training), obtaining a well-structured image-shape joint embedding space.
POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification
The automated machine learning (AutoML) field has become increasingly relevant in recent years.
Heterogeneous Datasets for Federated Survival Analysis Simulation
However, the data needed to train survival models are often distributed, incomplete, censored, and confidential.
Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits
Today, artificial neural networks are the state of the art for solving a variety of complex tasks, especially in image classification.
Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits
The use of Neural Architecture Search (NAS) techniques to automate the design of neural networks has become increasingly popular in recent years.
Federated Survival Forests
In this work, we present a novel federated algorithm for survival analysis based on one of the most successful survival models, the random survival forest.
A Multi-Modal Simulation Framework to Enable Digital Twin-based V2X Communications in Dynamic Environments
Digital Twins (DTs) for physical wireless environments have been recently proposed as accurate virtual representations of the propagation environment that can enable multi-layer decisions at the physical communication equipment.
Two Steps Forward and One Behind: Rethinking Time Series Forecasting with Deep Learning
The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision.
Few Shot Semantic Segmentation: a review of methodologies and open challenges
Semantic segmentation assigns category labels to each pixel in an image, enabling breakthroughs in fields such as autonomous driving and robotics.
Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques
These results represent a new state of the art in Classification Accuracy Score and highlight the effectiveness of post-processing techniques in improving the quality of synthetic datasets.
Discriminative Adversarial Privacy: Balancing Accuracy and Membership Privacy in Neural Networks
The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines.
Neural Architecture Transfer 2: A Paradigm for Improving Efficiency in Multi-Objective Neural Architecture Search
Deep learning is increasingly impacting various aspects of contemporary society.
Surgical fine-tuning for Grape Bunch Segmentation under Visual Domain Shifts
Mobile robots will play a crucial role in the transition towards sustainable agriculture.
Scaling Survival Analysis in Healthcare with Federated Survival Forests: A Comparative Study on Heart Failure and Breast Cancer Genomics
Our results underscore the potential of FedSurF++ to improve the scalability and effectiveness of survival analysis in distributed settings while preserving user privacy.
Continual Cross-Dataset Adaptation in Road Surface Classification
Accurate road surface classification is crucial for autonomous vehicles (AVs) to optimize driving conditions, enhance safety, and enable advanced road mapping.
RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline
The methodology undergoes evaluation across a variety of FMCW Radar dataset scenes, and it is compared to state-of-the-art systems such as Scan Context for Place Recognition and ICP for Loop Closure.
Age Group Discrimination via Free Handwriting Indicators
Content-free handwriting data from 80 healthy participants in different age groups (20-40, 41-60, 61-70 and 70+) were analysed.
Deep Learning-based Target-To-User Association in Integrated Sensing and Communication Systems
Simulation results over different urban vehicular mobility scenarios show that the proposed T2U method provides a probability of correct association that increases with the size of the BS antenna array, highlighting the respective increase of the separability of the VEs in the beamspace.
Can Shape-Infused Joint Embeddings Improve Image-Conditioned 3D Diffusion?
We find that, while matching CLIP in generation quality and diversity, CISP substantially improves coherence with input images, underscoring the value of incorporating 3D knowledge into generative models.
More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation
\acrlong{fss}, in particular, concerns the extension and optimization of traditional segmentation methods in challenging conditions where limited training examples are available.
Harnessing the Computing Continuum across Personalized Healthcare, Maintenance and Inspection, and Farming 4.0
The AI-SPRINT project, launched in 2021 and funded by the European Commission, focuses on the development and implementation of AI applications across the computing continuum.
A Deep-Learning Technique to Locate Cryptographic Operations in Side-Channel Traces
Side-channel attacks allow extracting secret information from the execution of cryptographic primitives by correlating the partially known computed data and the measured side-channel signal.
Latent Neural Cellular Automata for Resource-Efficient Image Restoration
Neural cellular automata represent an evolution of the traditional cellular automata model, enhanced by the integration of a deep learning-based transition function.
