|
|
@@ -1,5 +1,5 @@
|
|
|
+++
|
|
|
-title = "Can artificial intelligence generate new video content from text descriptions??"
|
|
|
+title = "Can artificial intelligence generate new video content from text descriptions?"
|
|
|
date = "2021-07-21T00:21:34+08:00"
|
|
|
tags = ["video marketing", "text to video"]
|
|
|
type = "blog"
|
|
|
@@ -7,6 +7,8 @@ categories = ["marketing"]
|
|
|
banner = "https://i.imgur.com/jdQb3ZH.jpg"
|
|
|
+++
|
|
|
|
|
|
+## Can artificial intelligence generate new video content from text descriptions?
|
|
|
+
|
|
|
**This project aims to build a deep learning pipeline that takes text descriptions and generates unique video depictions of the content described.**
|
|
|
|
|
|
The crux of the project lies with the Generative Adversarial Network, a deep learning algorithm that pins two neural networks against each other in order to produce media that is unique and realistic.
|
|
|
@@ -200,4 +202,4 @@ I believe this pipeline will run quite well on higher quality videos that stick
|
|
|
|
|
|
Additionally, I believe that tokenizing for the action words in the text descriptions and putting an additional focus on these word vectors during the embedding stage will prevent the contextual breakdown that this project faced.
|
|
|
|
|
|
-Changing video generation model to be more like the image generation one will also improve the results. The image generation model takes into account whether the image is a match with its text description when deriving the loss. The video generation needs a similar data and loss function design.
|
|
|
+Changing video generation model to be more like the image generation one will also improve the results. The image generation model takes into account whether the image is a match with its text description when deriving the loss. The video generation needs a similar data and loss function design.
|
