Awesome
Attentive Semantic Video Generation using Captions
Tensorflow implementation for the paper Attentive Semantic Video Generation using Captions by Tanya Marwah*, Gaurav Mittal* and Vineeth N. Balasubramanian accepted at International Conference on Computer Vision 2017 (ICCV 2017) (*Equal Contribution).
<figure> <img src="https://user-images.githubusercontent.com/28288044/31856492-58956022-b690-11e7-9acd-31076e91d50a.jpg" width="100%"> <figcaption>Proposed network architecture for attentive semantic video generation with captions. </figcaption> </figure>Results
| <img src="http://i.imgur.com/Gvsbu57.gif" width="100%"> | <img src="http://i.imgur.com/UaslWci.gif" width="100%"> |
|---|---|
| digit 6 is moving up and down | digit 3 is moving left and right |
| <img src="https://user-images.githubusercontent.com/28288044/31858691-12f254d0-b6cc-11e7-9f67-1b8aaa457028.gif" width="35%"> |
|---|
| person 4 is walking left to right |
Example of Spatio Temporal Style Transfer
| <img src="http://i.imgur.com/0QtyPSj.gif" width="70%"> |
|---|
| Caption 1: digit 4 is moving up and down Caption 2: digit 4 is moving left and right |
| <img src="http://i.imgur.com/usaRTaD.gif" width="100%"> | <img src="http://i.imgur.com/JiUM3HY.gif" width="100%"> |
|---|---|
| Caption 1: digit 4 is moving up and down Caption 2: digit 9 is moving left and right | Caption 1: digit 5 is moving left and right Caption 2: digit 9 is moving up and down |
| <img src="https://user-images.githubusercontent.com/28288044/31858692-12fd255e-b6cc-11e7-9da7-b85c1f0e54fc.gif" width="35%"> |
|---|
| Caption 1: person 10 is walking left to right Caption 2: person 10 is walking right to left |