Go to content Go to navigation Go to search

ICCV - Day 6

Final day of the main conference. There were some interesting oral sessions on motion and tracking, and face processing (as expected, none related to any sort of recognition, which is already a matured field by now). Some posters were far more interesting with some really novel advancements and potentially useful ideas for the future of computer vision — a new keypoint detector called BRISK (Stefan Leutenegger and colleagues from ETH Zurich) which seems to be far more robust than SIFT and SURF, and a new hierarchical representation model for understanding “‘Egocentric Activities’ (hand-object interactions)” by Jim Rehg and his students at Georgia Tech. There are probably a few more worth mentioning which I couldn’t immediately recall.

The great thing about a top conference like ICCV is the almost unreal fact that people still mingle around and attend sessions, there were hardly any blank poster boards and the same people still sit around having discussions or sorting out some code. If you know what exactly I’m trying to say, yeah, you get the exact opposite in almost any typical “ordinary” research conference, loaded with somewhat superfluous programmes held at typically exotic locations. Not that Barcelona isn’t exotic or touristy enough, but it sure amazes me how much enthusiasm and the level of seriousness these people have to try absorb as much as they could in one week. I for one, did actually sneaked out to the Spanish Village (Poble Espanyol) yesterday morning with Josiah when we didn’t quite fancy the session.

The next two days will see the return of more workshops.

Leave your comments

Remember
  You can enclose *strong* for strong or _emphasis_ for emphasis
Find out more at Textile Help
This is not SPAM

Live comment preview

wrote:

to be posted on 26 July 2017, 00:46

Subscribe to Tulips by Email

 » This article » 

Back to Archive list