🌟 Pretrain domain-specific models using visual instructions to enhance accuracy and performance in specialized tasks with ViTP.

This project combines weekly epidemiological case counts of pneumonic plague in Madagascar (Aug–Nov 2017) with Google Trends data for related search terms to explore how online interest tracks—and even predicts—disease spread.

Vision Foundation Models: SAM, ViT, CLIP, DINOv2, object detection, segmentation, and multimodal AI for computer vision.

SimpleAICV:pytorch training and testing examples.

A data-driven analysis applying Dynamic Mode Decomposition (DMD) to model complex dynamical systems for financial price prediction

Machine learning project for improving air quality prediction accuracy using regression models and optimizing MAE with Random Forest.

Foundation models based medical image analysis

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

Official implementation of MaeFuse （TIP 2025）

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

Disease Forecasting in a Tropical Context: A Comparative Evaluation of Model Performance and Generalizability for Dengue Fever and Influenza in Vietnam

A hands-on project for forecasting time-series with PyTorch LSTMs. It creates realistic daily data (trend, seasonality, events, noise), prepares it with sliding windows, and trains an LSTM to make multi-step predictions. The project tracks errors with RMSE, MAE, MAPE and shows clear plots of training progress and forecast results.

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

Estimativas globais de saúde: expectativa de vida e principais causas de morte e incapacidade.

Polynomial Regression from Scratch for Predicting Car Prices with Custom Evaluation Metrics and modular Architecture.

Baseline codebase for the FOMO25 Challenge at MICCAI2025

tool for compare and adjust images

Linear Regression from scratch.

Code for the seminar paper 'Self-Supervised Learning: MAE & DINOv2 Models and Practical Implementation' — Nishant Gupta, Technische Hochschule Ingolstadt, 2025.

EchoCardMAE: Video Masked Auto-Encoders Customized for Echocardiography