GitHub

A collection of tools and models designed to aid in the use of Computer Vision in baseball.

Our goal is to provide access to high-quality datasets and computer vision models for baseball. By sharing our annotated data and model weights, we hope to foster innovation in sports analytics and ...
GitHub

Two models for detecting and localizing stamps in document images, one based on traditional image processing techniques, and another using a YOLO-based deep learning approach.

To generate labeled data, I built a Streamlit application in this script label_images_app.py that uses a stamp detection algorithm based on traditional image processing techniques. This application ...
Frontiers

Multi-QuadEmoNet: cat and dog emotion classification model from animal vocalization using multi-stage LSTM-GRU paradigm

The self-collected audio dataset was split in the ratio of 80:20. The proposed Multi-QuadEmoNet and other methods are experimented using python 3.10.4 version. The software packages employed for this ...