Name: Luigi Celona
Type: User
Company: University of Milano-Bicocca
Bio: Assistant professor. Research interests: computer vision, deep learning, image quality, image aesthetics, face analysis.
Location: Milan - Italy
Blog: http://luigicelona.it
Luigi Celona's Projects
A beautiful, simple, clean, and responsive Jekyll theme for academics
ArabCeleb: Speaker Recognition in Arabic
Why DeepDive 🌊 Because the format is liquid 💦 😉
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
Source code for the paper "Blind Image Quality Assessment of Authentically Distorted Images"
C3D is a modified version of BVLC caffe to support 3D ConvNets.
Caffe: a fast open framework for deep learning.
Convert torch t7 model to pytorch model and source.
Email Client for reading and sending emails.
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Materials for the practical sessions at M2L
Reference code for the paper "Learning to Correct Overexposed and Underexposed Photos". Our method is a coarse-to-fine deep learning model to correct badly-exposed photographs.
Towards Simulating Foggy and Hazy Images and Evaluating their Authenticity
Google Research
PyTorch implementation of "Grid anchor based image cropping"
Image-to-Image Translation in PyTorch
PyTorch implementation Large-Margin Softmax (L-Softmax) loss
Code for the paper Benchmark Analysis of Representative Deep Neural Network Architectures
Master thesis on image denoising with the Natural Image Noise Dataset, convolutional neural networks, and generative adverserial networks.
darknet neural network addon for openFrameworks
Source code for "From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality"
Repository for tutorial sessions at EEML2020
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Reproducible experimental protocols for multimedia (audio, video, text) database
PyScopus
95.04% on CIFAR10 with PyTorch