1
$\begingroup$

I am reading Long-term Temporal Convolutions for Action Recognition and under the Section 3.1, I read this:

To investigate the impact of long-term temporal convolutions, we here study network inputs with different temporal extents.....

and then

As illustrated in Figure 2, the temporal resolution in our 60f network corresponds to 60, 30, 15, 7 and 3 frames for each of the five convolutional layers. In comparison, the temporal resolution of the 16f network is reduced more drastically to 16, 8, 4, 2 and 1 frame at each convolutional layer. We believe that preserving the temporal resolution at higher convolutional layers should enable learning more complex temporal patterns. The space-time resolution for the outputs of the fifth convolutional layers is $3 \times 3 \times 1$ and $1 \times 1 \times 3$ for the 16f and 60f networks respectively. The two networks have a similar number of parameters in the fc6 layer and the same number of parameters in all other layers. For a systematic study of networks with different input resolutions we also evaluate the effect of increased temporal resolution $t \in \{20, 40, 60, 80, 100\}$ and varying spatial resolution of $\{58 \times 58, 71 \times 71\}$ pixels.

How can we reduce temporal resolution of a ConvNet at each convolutional layer.

What does preserving the temporal resolutional mean and what does complex temporal resolution mean?

I've taken courses on Convolutional Neural Network and never heard of anything such as "temporal extent" or "temporal resolutions". Searching about them gives links to other research paper, which still use the term without describing its meaning.

Anyone, kindly put some light on it.

$\endgroup$
  • $\begingroup$ It might be the same as duration. $\endgroup$ – Yuval Filmus Feb 15 at 14:11
  • $\begingroup$ What kind of duration? Does it differs from the no. of frames per second? $\endgroup$ – Jos Feb 15 at 14:32
  • $\begingroup$ Number of frames per second is frequency. Duration is measured in units of time. For example, 1 second is a duration, while 20 frames per second is frequency. $\endgroup$ – Yuval Filmus Feb 15 at 14:33
  • $\begingroup$ Aah !! That's right. Found this $\endgroup$ – Jos Feb 15 at 14:43
  • 2
    $\begingroup$ Feel free to answer your own question, if you think you have found a better answer. $\endgroup$ – D.W. Feb 15 at 17:59
0
$\begingroup$

Temporal extent is the same as duration. It is measured in units of time, like second. For example, 1 second is a duration or temporal extent.

$\endgroup$
  • $\begingroup$ "Temporal extent refers to how much time a behavior takes up. For instance, if you are interested in measuring the behavior of crying, you can measure the duration of crying by starting a timer at the first sound of crying and ending the timer when the crying stops." source $\endgroup$ – Yuval Filmus Feb 15 at 16:38
  • $\begingroup$ What does that mean in the context of videos with the input of 60 frame or 16 frames? $\endgroup$ – Jos Feb 15 at 17:06
  • $\begingroup$ It might refer to the duration of a single frame, or of a certain event. You'll have to read the paper and figure out from context. $\endgroup$ – Yuval Filmus Feb 15 at 17:08

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.