[IJCV][ECCV2020 Spotlight] Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring

Predict if SpaceX Falcon 9 first stage will land successfully after rocket launches.

CVPR2023 | MVImgNet: A Large-scale Dataset of Multi-view Images

[CVPR2021] Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes

[CVPR2023] Blur Interpolation Transformer for Real-World Motion from Blur

A collection of real-world raw datasets used to practice data analysis, explore patterns, and generate actionable insights.

A machine learning and deep learning pipeline for fashion image classification. Combines real-world data, manual annotation, and both KNN and EfficientNet-B0 CNN models to classify images into style categories. Includes data cleaning, augmentation, model training, evaluation, and reproducible notebooks.

A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer” [TASLP 2024]

This repository contains code and data for the paper "TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering."

Linear Machine Learning Models for Predictive Analysis on Iowa Road Quality

This project showcases a complete data cleaning and basic analytics workflow on a real-world-style employee health dataset, simulating inconsistencies often found in raw data. It includes both uncleaned and cleaned Excel files, plus a pivot-based dashboard to derive insights.

HealthChat is a project containing a series of ongoing efforts to improve health conversations involving humans and AI (e.g., LLMs).

🩺 A healthcare data project that combines information from multiple Excel sheets, cleans and prepares the data, explores patterns, and creates interactive dashboards to show key insights.

Working with a real world data-set using SQL (SQLite) and Python

ZelionTech official website – Verifiable real-world energy data — transparent, auditable records.

10 hrs live hackathon held at ZS Office amongst the Top 40 Emerging Data Scientists of the country.

Anomaly detection project utilizing CESNET-TimeSeries24 real-world network traffic data. Employs n_flows for comprehensive EDA, SARIMAX modeling, and LSTM-based forecasting to identify anomalous network behaviors. Focuses on time series analysis for robust detection

This is an automated mirror of the smdi package hosted on GitLab

Human real estate field execution services for AI-driven systems in Andalusia, Spain.

Data analysis on Uber ride data using Python and visualization libraries.