Yuki Asano | Self-Supervision | Self-Labelling | Labelling Unlabelled videos from scratch w multi-modal self-supervision | CV | CTDS.Show #81

Video Link: https://youtu.be/LPdbnasJ9wI

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani

In this episode, Sanyam Bhutani interviews Computer Vision Researcher at the Oxford VGG Group: Yuki Asano.

They talk all about Yuki's journey into Computer Vision and his research interests, how Yuki approaches research.

They also discuss three of Yuki's recent works and Yuki walks us through the process of how he approached the projects, along with an interesting overview of the same.

Links:

A critical analysis of self-supervision, or what we can learn from a single image: https://arxiv.org/abs/1904.13132

Self-labelling via simultaneous clustering and representation learning: https://arxiv.org/abs/1911.05371

Labelling unlabelled videos from scratch with multi-modal self-supervision: https://arxiv.org/abs/2006.13662

Follow:

Yuki Asano:

https://twitter.com/y_m_asano

https://www.linkedin.com/in/yuki-m-asano/

https://yukimasano.github.io

Sanyam Bhutani:

https://twitter.com/bhutanisanyam1

Blog: sanyambhutani.com

About:

https://sanyambhutani.com/tag/chaitimedatascience/

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani.

You can expect weekly episodes every available as Video, Podcast, and blogposts.

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Intro track:

Flow by LiQWYD https://soundcloud.com/liqwyd