1

I need some explanation about the following paragraph (page 3) from the paper A Novel Approach for Robust Multi Human Action Detection and Recognition based on 3-Dimentional Convolutional Neural Networks.

We introduce a 3D convolution neural network with the following notations: $I(x, y, d)$ as an input video with a size of $x y$ and $d$ the temporal depth

What is "temporal depth"? Is it the number of frames?

nbro
  • 39,006
  • 12
  • 98
  • 176
Ahmed Hanan
  • 21
  • 4

1 Answers1

1

Temporal Depth is a third parameter of a time series data. For example if you have a video clip of length 25 frames and on training a model you are giving first five frames with respect to time. Your temporal depth will be 5.

Ahmed Hanan
  • 21
  • 4