Object detection and tracking algorithm implemented for Real-Time video streams and static images.

The AVA dataset densely annotates 80 atomic visual actions in 351k movie clips with actions localized in space and time, resulting in 1.65M action labels with multiple labels per human occurring fr…

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Papers, code and datasets about deep learning and multi-modal learning for video analysis

Work in progress Wiki for modding Monster Hunter Rise.

C#-based set of tools for WWise audio editing (generally for Capcom games).

Monster Hunter Rise Damage Calculations and Set Builder

A suite of tools used to generate pages for the Monster Hunter Wiki.

Generate a SQLite file from MHW data

YOLOv8 re-implementation for human detection using PyTorch

The dataset for drone based detection and tracking is released, including both image/video, and annotations.

Multi Person Skeleton Based Action Recognition and Tracking

Welcome to the YOLOv8 Human Detection Beginner's Repository – your entry point into the exciting world of object detection! This repository is tailored for beginners, providing a straightforward im…

Four Federated learning datasets for Human Activity Recognition

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

MT3: Multi-Task Multitrack Music Transcription

Python library for audio and music analysis

music21 is a Toolkit for Computational Musicology

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

Script for retrieving images and annotations (for all or only certain labels) from a COCO format dataset, and convert them to a YOLOv8 format dataset. The newly generated dataset can be used with U…

Convert JSON annotations into YOLO format.

👻 A curated list of awesome VLC and LibVLC resources.

A curated list of plugins that you can add to your FiftyOne install!

Convert a subtitle file (eg. .vtt, .srt files) to an .lrc file

Gamepads latency and polling rate tester (XinputTest analog)

2D vector & raster editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow.