Search Results for author: Christian Micheloni

Found 32 papers, 10 papers with code

Tracking Skiers from the Top to the Bottom

no code implementations15 Dec 2023 Matteo Dunnhofer, Luca Sordi, Niki Martinel, Christian Micheloni

To enable the study, the largest and most annotated dataset for computer vision in skiing, SkiTB, is introduced.

Visual Object Tracking

UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization

no code implementations2 Feb 2023 Rita Pucci, Christian Micheloni, Niki Martinel

The degradation in the underwater images is due to wavelength-dependent light attenuation, scattering, and to the diversity of the water types in which they are captured.

Image Enhancement Quantization

Real Image Super-Resolution using GAN through modeling of LR and HR process

no code implementations19 Oct 2022 Rao Muhammad Umer, Christian Micheloni

The current existing deep image super-resolution methods usually assume that a Low Resolution (LR) image is bicubicly downscaled of a High Resolution (HR) image.

Image Super-Resolution

Visual Object Tracking in First Person Vision

no code implementations27 Sep 2022 Matteo Dunnhofer, Antonino Furnari, Giovanni Maria Farinella, Christian Micheloni

Despite a few previous attempts to exploit trackers in the FPV domain, a methodical analysis of the performance of state-of-the-art trackers is still missing.

Human-Object Interaction Detection Object +2

CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking

no code implementations9 May 2022 Matteo Dunnhofer, Christian Micheloni

How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking.

Visual Object Tracking Visual Tracking

RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network

1 code implementation25 Oct 2021 Rao Muhammad Umer, Christian Micheloni

Modern digital cameras and smartphones mostly rely on image signal processing (ISP) pipelines to produce realistic colored RGB images.

Image Super-Resolution

Resolution based Feature Distillation for Cross Resolution Person Re-Identification

no code implementations16 Sep 2021 Asad Munir, Chengjin Lyu, Bart Goossens, Wilfried Philips, Christian Micheloni

Most of the existing approaches resolve the re-id task as low resolution problem in which a low resolution query image is searched in a high resolution images gallery.

Image Super-Resolution Person Re-Identification

Is First Person Vision Challenging for Object Tracking?

no code implementations31 Aug 2021 Matteo Dunnhofer, Antonino Furnari, Giovanni Maria Farinella, Christian Micheloni

Our study extensively analyses the performance of recent visual trackers and baseline FPV trackers with respect to different aspects and considering a new performance measure.

Human-Object Interaction Detection Object +2

A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolution

no code implementations7 Jul 2021 Rao Muhammad Umer, Asad Munir, Christian Micheloni

The existing SR methods have limited performance due to a fixed degradation settings, i. e. usually a bicubic downscaling of low-resolution (LR) image.

Generative Adversarial Network Image Super-Resolution

Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

no code implementations26 Mar 2021 Matteo Dunnhofer, Niki Martinel, Christian Micheloni

Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications.

Domain Adaptation Knowledge Distillation +2

Collaboration among Image and Object Level Features for Image Colourisation

no code implementations19 Jan 2021 Rita Pucci, Christian Micheloni, Niki Martinel

Image colourisation is an ill-posed problem, with multiple correct solutions which depend on the context and object instances present in the input datum.

Object

Is It a Plausible Colour? UCapsNet for Image Colourisation

1 code implementation4 Dec 2020 Rita Pucci, Christian Micheloni, Gian Luca Foresti, Niki Martinel

Different from existing works relying on convolutional neural network models pre-trained with supervision, we cast such colourisation problem as a self-supervised learning task.

Self-Supervised Learning

Is First Person Vision Challenging for Object Tracking?

no code implementations24 Nov 2020 Matteo Dunnhofer, Antonino Furnari, Giovanni Maria Farinella, Christian Micheloni

Despite a few previous attempts to exploit trackers in FPV applications, a methodical analysis of the performance of state-of-the-art visual trackers in this domain is still missing.

Human-Object Interaction Detection Object +2

Deep Iterative Residual Convolutional Network for Single Image Super-Resolution

1 code implementation7 Sep 2020 Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities.

Image Super-Resolution

Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution

1 code implementation7 Sep 2020 Rao Muhammad Umer, Christian Micheloni

We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions, which is inspired by the recent success of CycleGAN in the image-to-image translation applications.

Generative Adversarial Network Image Super-Resolution +2

Tracking-by-Trackers with a Distilled and Reinforced Model

1 code implementation8 Jul 2020 Matteo Dunnhofer, Niki Martinel, Christian Micheloni

Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers.

Knowledge Distillation Visual Object Tracking +1

Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution

1 code implementation3 May 2020 Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni

Most current deep learning based single image super-resolution (SISR) methods focus on designing deeper / wider models to learn the non-linear mapping between low-resolution (LR) inputs and the high-resolution (HR) outputs from a large number of paired (LR/HR) training data.

Generative Adversarial Network Image Super-Resolution

An Efficient UAV-based Artificial Intelligence Framework for Real-Time Visual Tasks

no code implementations13 Apr 2020 Enkhtogtokh Togootogtokh, Christian Micheloni, Gian Luca Foresti, Niki Martinel

In this paper we focus on this challenge and introduce a multi-layer AI (MLAI) framework to allow easy integration of ad-hoc visual-based AI applications.

object-detection Object Detection

Video-Based Convolutional Attention for Person Re-Identification

no code implementations26 Sep 2019 Marco Zamprogno, Marco Passon, Niki Martinel, Giuseppe Serra, Giuseppe Lancioni, Christian Micheloni, Carlo Tasso, Gian Luca Foresti

In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras.

Video-Based Person Re-Identification

Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations

no code implementations9 Sep 2019 Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni

Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image.

Image Super-Resolution

Wide-Slice Residual Networks for Food Recognition

4 code implementations20 Dec 2016 Niki Martinel, Gian Luca Foresti, Christian Micheloni

We believe that better results can be obtained if the deep architecture is defined with respect to an analysis of the food composition.

Image Classification

Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis

no code implementations ICCV 2015 Jorge Garcia, Niki Martinel, Christian Micheloni, Alfredo Gardel

In this paper, we focus on such a problem and introduce an unsupervised ranking optimization approach based on discriminant context information analysis.

Metric Learning Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.