Here is my list of the top 10 most interesting computer vision research papers of 2020.
In short, it is basically a curated list of the latest breakthroughs in AI and CV with a clear video explanation, link to a more in-depth article, and code (if applicable).
Enjoy the video, and let me know if I missed any important papers in the comments, or by contacting me directly on LinkedIn!
Watch the video
References
The top 10 computer vision papers in 2020 with video demos, articles, code, and paper reference.
The GitHub repository: https://github.com/louisfb01/Top-10-Computer-Vision-Papers-2020
Watch the AI Rewind 2020: https://youtu.be/DHBclF-8KwE
Video Transcript
00:00
computer vision the goal of computer
00:02
vision is to understand the content of
00:05
images
00:05
while it's trivial for humans it's a
00:08
whole other deal for a computer
00:10
and therefore it's one of the biggest
00:12
fields involving machine learning
00:14
basically it involves developing methods
00:17
that attempt to reproduce the capability
00:19
of human vision
00:20
which is the perfect challenge for
00:22
machine learning since
00:24
it already tries to reproduce the way
00:26
humans learn
00:27
that is why machine learning and deep
00:29
learning is so
00:30
tied up with computer vision such
00:33
applications may involve extracting an
00:35
object from the image
00:36
a text description a three-dimensional
00:39
model and so on
00:40
in short computer vision is a huge field
00:43
of study where we try to give
00:45
vision to computers using cameras basic
00:48
algorithms
00:49
filters and much more it has been
00:51
improved a lot recently
00:53
using machine learning algorithms to
00:55
achieve its goal of
00:56
understanding images