colincsl

I used to (almost) exclusively use Python and didn't like that I had to go bath and forth with Cython to make my models fast. Earlier this year I ported some of my code to Julia and feel more productive because of it. I feel like it's easier for me to implement new non-trivial improvements to my models than it was before.

For what it's worth I still stick with Python for computer vision applications. I mostly use Julia for timeseries models (e.g. Semi Markov CRFs) where it's harder to vectorize everything.

If I were restart again I'm not sure if I would suggest going the Julia route. I know there are alternatives like Numba that enable you write efficient code with minimal effort. Overall I like Julia as a language but there are a lot of little issues due to it being a new language.

I assume he's referring to Qt.

You're right that the video looks very impressive. However, I'm hesitant to believe that this actually works as well as one might perceive. In this area (called semantic segmentation in the computer vision world) it is common for a people to highlight both the good cases (where the labels/segmentation are correct) and the bad cases (where they are incorrect). In the MS video they only show the good. It's easy to cherry-pick examples where it works -- even if the overall accuracy is very low.

Furthermore, I don't know which dataset they're using. Perhaps it only works on a small set of objects such as those shown in the video.

I don't mean to knock their results but it will still take time to get this to work on a more broad set of videos.

I don't know much about PeerJ but I'm intrigued by their efforts as a publishing company to foster open collaborations like this.

I've only been watching from the Deep Learning sidelines -- but I believe people have steered away from pretraining over the past year or two. I think on practical datasets it doesn't seem to help.

As a robotics/computer vision researcher I disagree with you. The first Kinect was a godsend for robotics - previously it cost thousands of dollars for similar types of sensors. Typically we just want the raw data so that we can do whatever processing we want. It was nice because it worked on Mac/Linux/Windows without too much hassle. The new Kinect on the other hand is of little use to me right now. It's locked down on Windows - and as far as I know you need the special dev kit version for it to even work.

Also, a "cheap camcorder" is nothing compared to this. The Kinect is a 3D sensor. You would need 2 "cheap camcorders," stereo vision algorithms/hardware to process it in real-time, and even then the quality typically wouldn't be as good as the Kinect.

Tangentially, it's also disheartening (at least for the time being) that Apple recently bought Primesense - the maker of the original Kinect. Primesense was selling a better 3D sensor for developers/researchers. Apple shut it down as soon as they bought them.

In Europe you typically need a masters degree before you start a PhD program. In the US you don't - you can think of it as a 2+3 type program where you spend the first couple of years taking classes (and getting your masters) and the next three doing your thesis.

I just tried Go Dance (an ios game that uses the Extreme Reality engine) with artwork in the background and it worked well enough.

I guess I often assume that topics classes like these assume some sort of background in machine learning. Perhaps that's not the case.

I am surprised that there is no mention of this in the course syllabus -- in fact it looks like a lot of recent techniques that are missing. They don't even talking about LSA(/SVD)-based methods until the end of the course.