VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Adversarial Patch defense using SegmentAndComplete (SAC) & Masked AutoEncoder (MAE)

Implementation of a simple linear regression with single feature

Investigating Gradient Descent behavior in linear regression

Book Recommendation System

This is a warehouse for MAE-pytorch-models, can be used to train your dataset

This project provides a tool to compare two images using various similarity metrics, including histograms, structural similarity index (SSIM), mean squared error (MSE), mean absolute error (MAE), feature matching, and image hashing.

self-supervised learning

Develop a deep learning model capable of predicting traffic flow in urban environments. The model will utilize historical traffic data, weather conditions, and road configurations to forecast traffic patterns. This information can be invaluable for traffic management systems, helping to optimize traffic signals and reduce congestion, ultimately.

Semi-supervised Object Detection with MAE

[SHREC24] Skeleton-based Self-Supervised Learning For Dynamic Hand Gesture Recognition

A recommendation system for Restaurants!

keras implementation of vision transformers

code for "AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+"

Early stages of incorporating self-supervised with algorithm unrolling. Code was written as part of a master's thesis (60 ECTS) at Aalborg University, Denmark.

A simple recommender system in python implementing: ItemKNN, UserKNN, ItemAverage, UserAverage, UserItemAverage, etc.

Evaluate Video Salient Object Detection Via Python And Cuda !

Official code for CVPR2024 “VideoMAC: Video Masked Autoencoders Meet ConvNets”