Jump to: navigation, search

Youtube search... ...Google search

Image Captioning Through Neural Networks
An image captioning model using VGG16 feature extraction (CNN) and LSTM (RNN) neural networks. With Python, [TensorFlow]] and Keras

Automated Image Captioning with ConvNets and Recurrent Nets
Andrej Karpathy and Fei-Fei Li ...

A Simple Way to Automatically Transcribe Video/Audio to Text
Here is how to auto generate subtitles from any video with Google docs. It also works if you want to convert audio to text. Useful for creating subtitles and closed Captions for all your Youtube videos. The trick here is to make the recording and playback devices same. This will give good quality and help you automatically transcribe video to text.

Generating Captions from Images with Deep Learning
Ronjon Nag speaks for first part about the history of neural networks in industry. Dave Sullivan speaks for the second part and explains how to use neural networks to generate captions from images

Level Up - Automated Subtitles with AI
Welcome to Level Up! the show where we show you how to build solutions hands-on with Google Cloud Platform. In this episode, Solutions Architect Markku Lepistö will show you how to create subtitles for videos using Cloud AI services. And then how to translate the subtitles to quickly add support for multiple languages!

00:35 - Example of extracting the dialog as an audio track 01:15 - Enable Google Cloud AI services 02:37 - Coding the client app in Python 09:20 - Reviewing the results 09:48 - Uploading subtitles to YouTube Studio 10:44 - Testing the results

AI-Driven Image Captioning For Inclusive Productivity
Advances in hybrid intelligence, deep learning, and related artificial intelligence techniques have provided us with a remarkable opportunity to ensure the future of work will be even more inclusive to more people than ever before. Because the communication and products of work increasingly comprise images—photos, charts, maps, and the like—that are often not accessible, people who are blind or low vision face unique challenges. One promising technology is the automated understanding and captioning of images. Microsoft Office 365 applications, for example, can use APIs from Microsoft Azure Cognitive Services to automatically add alt text to images. But there remain many hurdles to making these captions truly useful and usable. In this breakout session, we will explore the state of the art and potential for advancement in automated image captioning, including data capture and curation for training, caption presentation and interactivity, and computer vision.

Microsoft AI breakthrough in automatic image captioning
Microsoft researchers have built an artificial intelligence system that can generate captions for images that are, in many cases, more accurate than what was previously possible. The breakthrough is a milestone in Microsoft’s push to make its products and services inclusive and accessible to all users.

Pytorch Image Captioning Tutorial
In this tutorial we go through how an image captioning system works and implement one from scratch. Specifically we're looking at the caption dataset Flickr8k. There are multiple ways to improve the model: train a larger model (the one used is relatively small), train for longer and improve the model by adding attention similar to this paper: Video of dataset (link in that video description to download the dataset yourself): Support My Channel Through Patreon: