Login / Signup
Multi-stream network with key frame sampling for human action recognition.
Limin Xia
Xin Wen
Published in:
J. Supercomput. (2024)
Keyphrases
</>
multi stream
key frames
hidden markov models
video retrieval
audio visual
video data
machine learning
action recognition
visual information
video content
visual content
image processing
feature vectors
audio visual speech recognition
key frame selection