Dmitriy Anisimov's profile - activity

overview network karma followed questions activity

2015-02-27 06:41:04 -0600	commented answer	face recognition challenge: train/test sets yes, let leave it as is. One my PR from the end of December still waiting in open state too.
2015-02-27 04:13:58 -0600	commented answer	face recognition challenge: train/test sets I took a look on it, but I can't merge OpenCV PR's and looks like currently there are some higher priority tasks, as there are already several unmerged PRs related to Challenge's code.
2015-02-20 06:34:59 -0600	answered a question	Vision challenge: tracking and Pedestrian Detection sure :) dataset page related to the implemented code in module dataset, so it has some additional code like "Pedestrian Detection", on the other hand we didn't implement code for tracking dataset, as it already has its own code. Briefly, "Pedestrian Detection" not covered by the Challenge and "Tracking" - covered.
2015-02-20 05:50:39 -0600	commented answer	face recognition challenge: train/test sets "i'd try a pr, if that halfway meets your ideas." sure, the addition of such command option was the first thing I thought too.
2015-02-20 03:21:01 -0600	answered a question	face recognition challenge: train/test sets For some reasons I didn't see your question earlier. I double checked description here. So pairsDevTrain.txt and pairsDevTest.txt should be used for parameters selection and as we don't choose parameters they shouldn't be used. And you are right: for reporting result each split from pairs.txt should be tested against the 9 other splits (train). p.s. whole my idea with benchmarks was to implement some solution for each Challenge's building block using only OpenCV. I had time on implementation 3 benchmarks and I hoped that OpenCV community may implement some others :)
2015-02-19 03:27:40 -0600	answered a question	vision challenge - submission There is no submission form or standard form of the paper (and there is no limitation on its maximum length), but all requirements for the submission are described in document on Vision Challenge wiki and also in the first question\answer of the Q&A section there. Material for the challenge should be sent to the Challenge e-mail: [email protected].
2014-11-23 07:02:26 -0600	received badge	● Enlightened (source)
2014-11-23 07:02:26 -0600	received badge	● Good Answer (source)
2014-11-21 04:47:42 -0600	answered a question	face recognition challenge: how to run the benchmark here: datasets/samples/fr_lfw_benchmark.cpp
2014-11-20 05:17:14 -0600	received badge	● Nice Answer (source)
2014-09-30 16:59:45 -0600	received badge	● Teacher (source)
2014-09-30 12:17:00 -0600	received badge	● Editor (source)
2014-09-29 03:11:43 -0600	answered a question	Vision Challenge is unnoticed Briefly: yes, challenge was postponed. The main reason, I think, is that there is no clear vision, what algorithms should win: with best performance from all challenge participants, close to the state of the art or newly developed with performance above current SOTA, fastest and close to SOTA, etc. Finally, OpenCV Vision Challenge was announced!