This is a repository that implements the Dense NN Retrieval Evaluation used for evaluating the In-Context Learning Capabilities of Vision Encoders.

iQRL: implicitly Quantized Representations for Sample-efficient Reinforcement Learning

2D Image Transformations (Rotation and Scaling) Using Log-Polar Mapping

This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video""

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

An Emacs framework for the stubborn martian hacker

Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition - BMVC 2018

Teaching material that I prepared as a TA for the laboratories of the Network Dynamics and Learning course for the MSc in Data Science and Engineering at Politecnico di Torino.

Datasets, Transforms and Models specific to Computer Vision

My default template for CLion C++ projects.

Learned Contextual Feature Reweighting for Image Geo-Localization (CVPR 2017)

Apply triplet loss to face recognition， adding new loss layer to the latest version of caffe.