Archives
Categories
- blogging (4)
- career (9)
- heritage (2)
- learning (1)
- leisure (1)
- publications (15)
- science (25)
- technology (20)
-
Top Posts
Tags
3-way trees academic world action recognition Ana Lopes application outsourcing Arnaldo Araújo back to work Brazil career in science cbir conference cooperation cultural heritage DCC / UFMG doceng France Fábio Faria image identification indexing kNN search linux machine learning Mac OS X macports mathematics multicurves office suites operating systems paper programming languages projection kd-forests publication retroblogged Ricardo Torres SBBD seminar sibgrapi tech for scholars thesis tutorial UNICAMP usability virtualization web 2.0 windowsMeta
Category Archives: science
After SOPA / PIPA, RWS
The appalling Research Works Act, in the harsh words of The Guardian, is the moment academic publishers gave up all pretense of being on the side of scientists. I, for myself, never believed their good intentions. Continue reading
Posted in science
Tagged open access, public access, Research Works Act, scientific politics, scientific publishing
Leave a comment
Recently accepted papers on ICIP and SIBGRAPI
I had a paper accepted on ICIP, the IEEE International Conference on Image Processing, and two papers accepted on our counterpart national conference, SIBGRAPI. Continue reading
Scientific sense and hurt sensibilities
(…) recently, I had a tough choice to make. A student was to submit his Master disstertation to the viva-voce committee, and, as it usually happens in Brazil, he has sent me a draft for corrections and suggestions. His “Results” chapter contained, among cold graphs and tables, several very explicit images, illustrating in detail the cases of success and failure of our [pornography detection] algorithm. The only thing is: all images contained censor bars. Continue reading
Posted in science
Tagged censorship, computer vision, pornography, pornography detection, self-censorship
7 Comments
Supertasks: Revisiting Cantor’s Diagonal
Take that famous proof of the existence of uncountable infinite sets, by Cantor, the (in)famous diagonal argument (I will be quoting heavily from that Wikipedia article). I love that proof, and I remember how wonderful I found it when I saw it for the first time. But the more I think about it, the less watertight it starts to look. Continue reading
Posted in science
Tagged cantor, cardinals, diagonalization, infinite, mathematics, ordinals, paradox, supertask
Leave a comment
A Survey on Human Action Recognition in Videos
Ana Lopes, Prof. Arnaldo Araújo, Prof. Jussara de Almeida and I have submitted a survey on human action recognition to CVIU. The paper proposes a new organizing framework, using the underlying data representation as the main criterium, a choice which emphasizes the hypothesis assumed and thus, the constraints imposed on the type of video that each technique is able to address. A preprint is available. Continue reading
Posted in science
Tagged action recognition, Ana Lopes, Arnaldo Araújo, CVIU, DCC / UFMG, human actions, Jussara de Almeida, paper, publication, survey
Leave a comment
Paper Accepted at ICPR 2010
Our paper, “MONORAIL: A Disk-Friendly Index for Huge Descriptor Databases” was accepted at the ICPR 2010 conference. I am particularly proud of this paper, not only because of the method itself, but because of the experimental design we propose for the validation. Continue reading
Posted in publications, science
Tagged conference, design of experiments, Fernando Akune, kNN search, monorail, paper, publication, Ricardo Torres
Leave a comment
Back from the USA
I have just arrived (suitcases still to be undone) from my trip to the USA, where I have presented at the ACM MIR 2010 and visited the campus of Virginia Tech. Continue reading
Posted in career, science
Tagged bioinformatics, cooperation, Edward Fox, Fábio Faria, João Setúbal, MIR 2010, Nadia Kozievitch, Otávio Penatti, paper, publication, Ricardo Torres, UNICAMP, USA, Virginia Tech
2 Comments
RECOD Project Approved by FAPESP
Our new lab RECOD now has not only a cool name and logo but also money to finance its first two years of operation. We have just been informed that the Brazilian sponsoring agency FAPESP has approved our project. The … Continue reading
Posted in science
Leave a comment
Reasoning for Complex Data
The new lab — which we named RECOD — aims to embrace the research subjects of machine learning, multimedia retrieval and classification, multimodality and digital forensics. Continue reading
Posted in science
Tagged Anderson Rocha, digital forensics, Jacques Wainer, machine learning, multimedia, RECOD, Ricardo Torres, Siome Goldenstein, UNICAMP
Leave a comment
Paper Accepted at MIR 2010
Our paper, “Learning to Rank for Content-Based Image Retrieval” , was accepted at the upcoming ACM Multimedia Information Retrieval Conference (MIR 2010). I will be travelling to Philadelphia on late March to present the poster. Continue reading
Posted in publications, science
Tagged cbir, conference, DCC / UFMG, Fábio Faria, learn to rank, machine learning, Marcos Gonçalves, MIR, paper, poster, publication, Ricardo Torres
Leave a comment