| Who | When |
Messages | |
|
|
|
| Adam
|
5
|
 |
|
10-24-2006 10:51 AM ET (US)
|
|
-I would would like to see how the other algorithms performed on the downsampled images. They handpicked their data for it to give the most information at low resolution.
-What are the applications of a very slow segmentation algorithm that only works well on previously picked easy data?
-Are the given results typical of RC and EJ algorithm segmentations? I don't know much about these algorithms, but it seems like they must be able to perform better than what is shown in fig 4.
|
| Nadav
|
6
|
|
|
10-24-2006 12:55 PM ET (US)
|
|
From the paper:
Run-time for
our current (Matlab) implementations is between 45 min.
and 1 hr. for the multi-scale method, and between 3 and
5 min. for the single-scale version. RC and EJ (both of
which are binary packages) take less than 1 min. to complete.
So their algorithm takes 45 min to run on 2 image? Or am I misunderstanding it? That seems very long.
-Nadav
|
| Joshua
|
7
|
|
|
10-24-2006 01:59 PM ET (US)
|
|
I am curious as to how similar the probability distributions found from the training data (e.g figures 1& 2) from the Berkely Segmentation Database will be to other training sets of natural images.
I.e. do these distributions work only for this particular dataset or do we have to re-train for every dataset?
|
| Deborah
|
8
|
|
|
10-24-2006 03:13 PM ET (US)
|
|
Can you explain the intuition of how Fourier coefficients represent a shape? Thank you!
|
Carolina Galleguillos
|
9
|
|
|
10-24-2006 04:45 PM ET (US)
|
|
They claim that the coarse estimate provides robustness to texture and clutter, but they use for training and testing only images that contain at least one salient, *unoccluded" object that is fully contained in the image.
|
| Tom
|
10
|
|
|
10-24-2006 04:52 PM ET (US)
|
|
I noticed that they didn't have any examples or real discussion (that I remember) of multi-object single background segmentation. Is that current work? Does it seem to anybody else like this algorithm couldn't be easily extended to do that?
(btw example would be two elephants on a savannah)
|
|
|
11
|
|
|
04-02-2009 02:09 AM ET (US)
|
|
Deleted by topic administrator 07-25-2009 02:12 AM
|
| robots
|
12
|
|
|
06-12-2009 07:37 AM ET (US)
|
|
|
| saaa
|
13
|
|
|
06-19-2009 10:20 PM ET (US)
|
|
christian louboutin Christian Louboutin web site. Luxury french shoe designer.Shop Christian Louboutin discount designer fashion at christian louboutinsale With the widest range of authentic luxury designer brands - It's Chic-onomics!
|
|
|
14
|
|
|
06-24-2009 05:10 AM ET (US)
|
|
Deleted by topic administrator 07-25-2009 02:12 AM
|
| Vwvmdjbu
|
15
|
|
|
07-15-2009 05:27 AM ET (US)
|
|
Jh0eL3
|
| |
Messages 16-18 deleted by topic administrator 08-03-2009 02:09 AM |
| incidence of sweating in
|
19
|
|
|
08-02-2009 04:21 PM ET (US)
|
|
H1DJIe If you have to do it, you might as well do it right.
|
| UGG Shoes
|
20
|
|
|
09-12-2009 09:49 PM ET (US)
|
|
|
