Which Deep Learning architecture is best for classifying short videos of variable length? I would like to classify videos that last from 1 up to 3 seconds.


My suggestion is to use Convolutional and Recurrent layers in the same Neural Network.

You'd have to capture a given number of frames of a video (let's say one each 0.5 seconds), and feed arrays of screenshots into the model. Its structure would be:

  1. Conv (and MaxPool) layers to process pixel data - they will extract and process relevant information from each screenshot.
  2. LSTM layers - that will process their sequence, extracting meaning from their flow.
  3. Dense layers at the end to perform classification, with softmax activation at the output layer.

That's how I would do. It's going to be computationally expensive, if you don't have a GPU it won't be easy.

| improve this answer | |
  • $\begingroup$ I was thinking something similar to this. Thank you so much for your help. $\endgroup$ – Stefan Radonjic Nov 12 '19 at 12:32
  • 1
    $\begingroup$ Glad to help, it looks like a really cool Computer Vision project $\endgroup$ – Leevo Nov 12 '19 at 13:48

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.