guglielmocamporese

awesome-action-prediction-list

A curated list of papers and resources linked to action anticipation and early action recognition from videos.

break_cifar10

Code for the Top-1 submission of contest of VCS AY 2020-2021, the Vision and Cognitive Service class, University of Padova, Italy.

cvaecaposr

Code for the Paper: "Conditional Variational Capsule Network for Open Set Recognition", Y. Guo, G. Camporese, W. Yang, A. Sperduti, L. Ballan, ICCV, 2021.

epic-kitchens-dataset-pytorch

Simple PyTorch Dataset for the EPIC-Kitchens-55 and EPIC-Kitchens-100 that handles frames and features (rgb, optical flow, and objects) for the Action Recognition and the Action Anticipation Tasks!

hands-segmentation-pytorch

A repo for training and finetuning models for hands segmentation.

learning_invariances_in_speech_recognition

In this work I investigate the speech command task developing and analyzing deep learning models. The state of the art technology uses convolutional neural networks (CNN) because of their intrinsic nature of learning correlated represen- tations as is the speech. In particular I develop different CNNs trained on the Google Speech Command Dataset and tested on different scenarios. A main problem on speech recognition consists in the differences on pronunciations of words among different people: one way of building an invariant model to variability is to augment the dataset perturbing the input. In this work I study two kind of augmentations: the Vocal Tract Length Perturbation (VTLP) and the Synchronous Overlap and Add (SOLA) that locally perturb the input in frequency and time respectively. The models trained on augmented data outperforms in accuracy, precision and recall all the models trained on the normal dataset. Also the design of CNNs has impact on learning invariances: the inception CNN architecture in fact helps on learning features that are invariant to speech variability using different kind of kernel sizes for convolution. Intuitively this is because of the implicit capability of the model on detecting different speech pattern lengths in the audio feature.

math-unipd-booking-bot

Simple and easy to use python BOT for the COVID registration booking system of the math department @ unipd (torre archimede). This API creates an interface with the official website, with more useful functionalities.

relvit

Official code of "Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer", Guglielmo Camporese, Elena Izzo, Lamberto Ballan. BMVC, 2022.

useful

Useful scripts/commands/settings I mostly use for research/work.

visual-transformer-pytorch

An easy and minimal implementation of the Visual Transformer (ViT) in PyTorch, from scratch!

guglielmocamporese/hands-segmentation-pytorch

A repo for training and finetuning models for hands segmentation.

guglielmocamporese/cvaecaposr

Code for the Paper: "Conditional Variational Capsule Network for Open Set Recognition", Y. Guo, G. Camporese, W. Yang, A. Sperduti, L. Ballan, ICCV, 2021.

guglielmocamporese/epic-kitchens-dataset-pytorch

Simple PyTorch Dataset for the EPIC-Kitchens-55 and EPIC-Kitchens-100 that handles frames and features (rgb, optical flow, and objects) for the Action Recognition and the Action Anticipation Tasks!

guglielmocamporese/relvit

Official code of "Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer", Guglielmo Camporese, Elena Izzo, Lamberto Ballan. BMVC, 2022.

guglielmocamporese/learning_invariances_in_speech_recognition

In this work I investigate the speech command task developing and analyzing deep learning models. The state of the art technology uses convolutional neural networks (CNN) because of their intrinsic nature of learning correlated represen- tations as is the speech. In particular I develop different CNNs trained on the Google Speech Command Dataset and tested on different scenarios. A main problem on speech recognition consists in the differences on pronunciations of words among different people: one way of building an invariant model to variability is to augment the dataset perturbing the input. In this work I study two kind of augmentations: the Vocal Tract Length Perturbation (VTLP) and the Synchronous Overlap and Add (SOLA) that locally perturb the input in frequency and time respectively. The models trained on augmented data outperforms in accuracy, precision and recall all the models trained on the normal dataset. Also the design of CNNs has impact on learning invariances: the inception CNN architecture in fact helps on learning features that are invariant to speech variability using different kind of kernel sizes for convolution. Intuitively this is because of the implicit capability of the model on detecting different speech pattern lengths in the audio feature.

guglielmocamporese/awesome-action-prediction-list

A curated list of papers and resources linked to action anticipation and early action recognition from videos.

guglielmocamporese/useful

Useful scripts/commands/settings I mostly use for research/work.

guglielmocamporese/math-unipd-booking-bot

Simple and easy to use python BOT for the COVID registration booking system of the math department @ unipd (torre archimede). This API creates an interface with the official website, with more useful functionalities.

guglielmocamporese/break_cifar10

Code for the Top-1 submission of contest of VCS AY 2020-2021, the Vision and Cognitive Service class, University of Padova, Italy.

guglielmocamporese/visual-transformer-pytorch

An easy and minimal implementation of the Visual Transformer (ViT) in PyTorch, from scratch!

guglielmocamporese/Speech-Classification-a-dictionary-approach-with-MFCC-and-Dynamic-Time-Warping

guglielmocamporese/deep-vector-quantization

What can we do with Vector Quantization on Deep Nets?

guglielmocamporese/glom

Minimal GLOM implementation in PyTorch.

guglielmocamporese/A-Deep-Introspection-on-Generative-Adversarial-Networks

Study and implementation of a GAN with Goodfellow’s approach.

guglielmocamporese/cartpole-deeprl-tf

Open AI Cartpole Solved in TensorFlow

guglielmocamporese/dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

guglielmocamporese/generative-dog-images

kaggle challenge on GANs for generating dog images

guglielmocamporese/gpu_benchmark

Benchmarks for testing GPUs.

guglielmocamporese/guglielmocamporese

guglielmocamporese/guglielmocamporese.github.io

guglielmocamporese/human_protein_atlas_image_classification

Kaggle Competition

guglielmocamporese/keras-targeted-dropout

Targeted dropout implemented in Keras

guglielmocamporese/kinetics-downloader

Download DeepMind's Kinetics dataset.

guglielmocamporese/moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

guglielmocamporese/rulstm

Code for the Paper: Antonino Furnari and Giovanni Maria Farinella. What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention. International Conference on Computer Vision, 2019.

guglielmocamporese/simsiam

PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

guglielmocamporese/singularity-create-image

guglielmocamporese/tinyAction

Baseline code for TinyAction Challenge

guglielmocamporese/tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

guglielmocamporese/visual-coding