Action Recognition Using Multi-stream 2D CNN with Deep Learning-Based Temporal Modality.

Keonwoo Kang Sangwoo Park Hasil Park Donggoo Kang Joonki Paik

Published in: ICCE (2023)

Keyphrases

deep learning
multi stream
audio visual
audio visual speech recognition
multi modal
unsupervised learning
unsupervised feature learning
machine learning
spatio temporal
hidden markov models
mental models
weakly supervised
human actions
space time
text classification
active learning
feature selection