The clash between two worlds in human action recognition: supervised feature training vs Recurrent ConvNet

The clash between two worlds in human action recognition: supervised feature training vs Recurrent ConvNet

Indiana University-Purdue University Indianapolis (IUPUI) === Action recognition has been an active research topic for over three decades. There are various applications of action recognition, such as surveillance, human-computer interaction, and content-based retrieval. Recently, research focuses...

Full description

Bibliographic Details
Main Author: Raptis, Konstantinos
Other Authors: Tsechpenakis, Gavriil
Language:en_US
Published: 2017
Subjects:
Action Recognition
Dense Trajectories
R-CNN
LSTM RNN
Convolution Neural Networks
Recurrent Neural Networks
Online Access:http://hdl.handle.net/1805/11827
https://doi.org/10.7912/C2CW7G

Internet

http://hdl.handle.net/1805/11827
https://doi.org/10.7912/C2CW7G

Similar Items