There are 11 article(s) in Research
07.01.12 Computer Vision Reading Groups
A strange thing to do when I just have the urge to nose around at what other computer vision (CV) people are reading. Doesn’t tell the whole story, but tunes me into some trending vibes and at times, a sudden kick in the arse.
Sticky goes here:
13.11.11 ICCV - Day 8
Final day of workshops, final day of ICCV.
I attended the 1st Workshop on Benchmarking Facial Image Analysis Technologies, which had an array of talks on the latest benchmarks and datasets for facial image analysis. Jonathon Phillips from NIST gave an overview of NIST face benchmarking and protocols including unveiling some upcoming video datasets for the next few years. The guys from NICTA Australia had a review on face biometric benchmarking, and some other interesting new datasets were presented for gender classification, 3D twins and expression challenges, partially occluded 3D faces and a couple of “in-the-wild” datasets for facial expression and facial landmarks (points).
Read on...
•
barcelona •
computer vision •
conference •
iccv2011 •
research •
workshop
12.11.11 ICCV - Day 7
Back to workshops today. One of those “forward-looking” days where there’s not much that is related to my current research, but lots to take in for future research!
I skipped around between two workshops: one on “‘socially intelligent surveillance and monitoring, which interests me quite a bit for future work, and another on live dense reconstruction from moving cameras (note: live), which is by far one of the most popular workshops of the day (with a room full of cameras, Kinect sensors and quad-core machines!) Here’s a picture of Shahram Izadi of Microsoft Research demonstrating a live scene reconstruction using a Kinect sensor.
Read on...
•
barcelona •
computer vision •
conference •
iccv2011 •
research •
workshop
11.11.11 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.
Read on...
•
barcelona •
computer vision •
conference •
iccv2011 •
research
10.11.11 ICCV - Day 5
Oral sessions on the third day of the main conference event was probably among the least interesting ones, at least for me and my area of work. The “light banquet” in the evening is probably the main attraction of the day, excellently staged at a great venue, and includes an interesting Catalonian castell, or human tower performance.
Read on...
•
barcelona •
castell •
computer vision •
conference •
iccv2011 •
research
09.11.11 ICCV - Day 4
Now that I’m free from my poster duties (but by no means, very tired from talking and standing), I got to take it easy, enjoy some good talks, pick up new ideas, and go check out some other posters and demos.
•
barcelona •
computer vision •
conference •
demo •
iccv2011 •
research
08.11.11 ICCV - Day 3
ICCV main conference officially started today. And, I had the strange luck of having my poster scheduled on the first day. Had a number of interested people coming over to check out my work, hopefully not to see how I’ve got 18 printed A4 sheets taped together to make a A0 sheet. Somehow it looked pleated, but who cares, it doesn’t cost much!
Read on...
•
barcelona •
computer vision •
conference •
iccv2011 •
poster •
research
07.11.11 ICCV - Day 2
Workshops start on the second day. There were 8 workshops running concurrently, and I was particularly interested in the PASCAL Visual Object Classes Challenges 2011, and really had to go check out what the CV community had been up to in the area of object classification.
Read on...
•
barcelona •
computer vision •
conference •
iccv2011 •
research •
workshop
06.11.11 ICCV - Day 1
Pre-conference events started with an attractive bunch of tutorials on Day 1.
- I had in mind to attend the very general, multi-topic, summary-of-field &#
Read on...
• barcelona • computer vision • conference • iccv2011 • research
11.10.11 Publish and pay or perish
Has academic publishing degenerated into a profit-making business? Why do the commercial publishers now have stranglehold over our research, and that we peons have at our very best, been doing too much for free?
Here’s a nice article I read from Times Higher Education by Mike Taylor, who summed up the entire process,
Read on...
•
academic •
peer review •
publishing •
research
06.10.11 Free online courses from Stanford
Stanford is offering free online courses in AI, Machine Learning and Databases, all of which require enrollment, participation in review questions, homework and computer assignments (optional though). Students will also get regular feedback on their progress, and get graded. We are talking about the scale of 10,000s or 100,000s if it really does get popular having Machine Learning with Andrew Ng, AI with Sebastian Thrun and Peter Norvig (Google), and Databases with Jennifer Widom.
Read on...
•
ai •
courses •
database •
machine learning •
stanford