3D photo is great, but have you ever seen 3D *free-viewpoint video*? Space-time neural rendering from a single, casually captured video!

https://youtu.be/2tN8ghNu2sI

Project page: https://video-nerf.github.io/

Paper: https://arxiv.org/pdf/2011.12950.pdf

Code: coming soon

NeurIPS 2020 is the largest machine learning conference and is just around the corner! Check out this exclusive collection of 100+ pre-recorded talks on the latest machine learning research from world-renowned tech companies and universities. Videos are shared by the authors with free public access

NeurIPS 2020 highlights at:
https://crossminds.ai/category/neurips%202020/

Also follow recent conferences and discover your inspirations and see what's happening

Montreal AI startup, Zetane, releases free software platform for the detailed analysis and visualization of popular deep learning models used in industry and research. By opening up black-box algorithms, diverse professionals gain new means to collaborate on applied machine Learning projects.

Blog:
https://medium.com/zetane-blog/free-software-platform-to-facilitate-collaboration-and-accelerate-adoption-of-ai-in-industry-c629247037b0

Project Page:
https://zetane.com/gallery

Project Page:
https://github.com/TZYSJTU/Sketch-Generation-with-Drawing-Process-Guided-by-Vector-Flow-and-Grayscale

Paper:
https://arxiv.org/pdf/2012.09004.pdf

TgStat team provided channel's progress for 2020 year. We are keeping growing in every categories: new members, global ranking, the average reach of each post, views per days, citation index when compared with previous year's statistics.

We will try our best to provide cutting edge of Artificial Intelligence for AI lovers.

Thank you for all subscribers and Thank you for being with us.

A new video shows a crew of Boston Dynamics robots busting some impressive dance moves.

IMHO: That advances of technology have also led to fears that the robots could become tools of repression or even Terminator-like killing machines.
Maybe that’s why they picked this particular song by The Contours — which is definitely a bop, but also contains the plaintive lines:
Do you love me
Now that I can dance

Super new addition to GANs
StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows

Github:
https://github.com/RameenAbdal/StyleFlow

Paper:
https://arxiv.org/pdf/2008.02401.pdf

Video explaining this paper:
https://www.youtube.com/watch?v=Lt4Z5oOAeEY

Photoshop detector AI called FALDetector aims to detect facial edits that warps the faces to make chin or jaw looks thinner, or the forehead smaller. However, it is not really accurate and consistent as it look at the individual pixels too much, as different resolution of the same person can result in different predictions with this AI model.

Transferable Interactiveness Networks (TIN) for Human-Object Interaction (HOI) Detection

Create Character Animation with small amount of data by using Generative Adversarial Network (GAN)

Github:

https://github.com/tohinz/CharacterGAN

Paper:

https://arxiv.org/pdf/2102.03141.pdf

You can use also interactive GUI to easily repose a given character based on keypoints.

End-to-end speech recognition toolkit (based on Pytorch)
What's make it different from other ASR toolkits:
* Production first and production ready
* Unified solution for streaming and non-streaming ASR
* Portable runtime
* Light weight