Facebook to Use AI to Recognize Videos

Facebook created VideoStory, a new dataset for video descriptions intended to help train systems that can automatically tell stories
01 November 2018   746

Videos have long been the main content of social networks. However, not all people can use them due to physical limitations. Therefore, Facebook developed the VideoStory system for teaching artificial intelligence so that it “automatically tells stories”.

The basis is a system that analyzes the video and creates detailed descriptions of the video. Technically, this is a set of sentences that describe in some detail what is happening. For data processing, a recurrent neural network was used, and about 20 thousand videos and 123 thousand sentences with descriptions were made as “educational material”. To do this, select the popular video from social networks.

The neural network itself had to take into account the connection between past and future events on the video, for which the researchers added an understanding of the context.

At the first stage, the system generated descriptions, although the proposals were often not related. However, potentially VideoStory can serve as a good guide for creating future systems describing what is happening on the screen. So far, the project itself has not been declared as commercial, therefore it is not known when it will be released as a finished application.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   676

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.