Video Classification with a CNN-RNN Architecture

Show and Tell
, ,
#1

How do we process videos to feed to a Deep Learning model and train it? Can we borrow concepts from image and text models and combine those to train a video classification model? Yes, we can.

My latest example on keras.io shows you how:

4 Likes
#2

Nice work Sayak!! Added to my to-read list!!

2 Likes
#3

A Transformer variant coming soon. Stay tuned, Gus :wink:

3 Likes
#4

Recently we have added MoViNets for Action Recognition on Mobile:

2 Likes
#5

Here’s the one: Video Classification with Transformers :open_hands:

2 Likes