Command Palette
Search for a command to run...
Parmar Paritosh ; Reddy Jaiden ; Morris Brendan

Abstract
Can a computer determine a piano player's skill level? Is it preferable tobase this assessment on visual analysis of the player's performance or shouldwe trust our ears over our eyes? Since current CNNs have difficulty processinglong video videos, how can shorter clips be sampled to best reflect the playersskill level? In this work, we collect and release a first-of-its-kind datasetfor multimodal skill assessment focusing on assessing piano player's skilllevel, answer the asked questions, initiate work in automated evaluation ofpiano playing skills and provide baselines for future work. Dataset isavailable from: https://github.com/ParitoshParmar/Piano-Skills-Assessment.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| audio-classification-on-multimodal-pisa | Audio | Accuracy (%): 64.50 |
| skills-assessment-on-multimodal-pisa | MMDL | Accuracy (%): 74.60 |
| video-classification-on-multimodal-pisa | Video | Accuracy (%): 73.95 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.