scholarly journals Spacetime Forests with Complementary Features for Dynamic Scene Recognition

2013 ◽  
Author(s):  
Christoph Feichtenhofer ◽  
Axel Pinz ◽  
Richard Wildes
Keyword(s):  
Scene Recognition ◽  
Dynamic Scene

A Super Descriptor Tensor Decomposition for Dynamic Scene Recognition

2019 ◽  
Vol 29 (4) ◽  
pp. 1063-1076 ◽  
Author(s):  
Muhammad Rizwan Khokher ◽  
Abdesselam Bouzerdoum ◽  
Son Lam Phung
Keyword(s):  
Tensor Decomposition ◽  
Scene Recognition ◽  
Dynamic Scene

scholarly journals HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN

Signals ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 604-618
Author(s):  
Paritosh Parmar ◽  
Brendan Morris
Keyword(s):  
Neural Networks ◽  
State Of The Art ◽  
Scene Recognition ◽  
Multitask Learning ◽  
Training Phase ◽  
Dynamic Scene ◽  
Improve Performance ◽  
Computing Power ◽  
Practical Standpoint ◽  
3D Cnn

Spatiotemporal representations learned using 3D convolutional neural networks (CNN) are currently used in state-of-the-art approaches for action-related tasks. However, 3D-CNN are notorious for being memory and compute resource intensive as compared with more simple 2D-CNN architectures. We propose to hallucinate spatiotemporal representations from a 3D-CNN teacher with a 2D-CNN student. By requiring the 2D-CNN to predict the future and intuit upcoming activity, it is encouraged to gain a deeper understanding of actions and how they evolve. The hallucination task is treated as an auxiliary task, which can be used with any other action-related task in a multitask learning setting. Thorough experimental evaluation, it is shown that the hallucination task indeed helps improve performance on action recognition, action quality assessment, and dynamic scene recognition tasks. From a practical standpoint, being able to hallucinate spatiotemporal representations without an actual 3D-CNN can enable deployment in resource-constrained scenarios, such as with limited computing power and/or lower bandwidth. We also observed that our hallucination task has utility not only during the training phase, but also during the pre-training phase.

Dynamic Scene Recognition with Complementary Spatiotemporal Features

2016 ◽  
Vol 38 (12) ◽  
pp. 2389-2401 ◽  
Author(s):  
Christoph Feichtenhofer ◽  
Axel Pinz ◽  
Richard P. Wildes
Keyword(s):  
Scene Recognition ◽  
Dynamic Scene ◽  
Spatiotemporal Features

scholarly journals Dynamic Scene Recognition Using Spatiotemporal Based DLTP on Spark

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 66123-66133 ◽  
Author(s):  
Md Azher Uddin ◽  
Mostafijur Rahman Akhond ◽  
Young-Koo Lee
Keyword(s):  
Scene Recognition ◽  
Dynamic Scene
Sign in / Sign up

Export Citation Format

Share Document