Multi-Modal Deep Learning-Based Violin Bowing Action Recognition.

Bao-Yun Liu Yi-Hsin Jen Shih-Wei Sun Li Su Pao-Chi Chang

Published in: ICCE-TW (2020)

Keyphrases

multi modal
action recognition
deep learning
human actions
unsupervised learning
bag of words
computer vision
machine learning
high dimensional
mental models
weakly supervised
video search
object detection
image annotation
supervised learning
co occurrence
medical images
information extraction