20 Questions 22 Answers 0 Followers
Questions related from Eren Golge
I have only the positive class images right now and I am trying to come up with a large set of random images as a negative set. However, what would be a great resource for such bunch of images? Is...
07 July 2014 9,233 1 View
I am looking for state of the art methods to capture the human segments of images (mostly clothing images that are including only one person with natural a background, for example...
06 June 2014 8,946 3 View
Example cases can be football or basketball matches.
06 June 2014 5,310 6 View
What are the criterion of the given dataset that makes it suitable for L1 SVM instead of L2? I know that it is favorable to use large dimensional features with L1 SVM to utilize its implicit...
05 May 2014 6,720 2 View
I would like to experiment with one of the anomaly detection methods. What dataset could be a good benchmark?
12 December 2013 3,180 11 View
I hope to find some recent works on LVQ a.k.a supervised SOM networks and successful applications.
12 December 2013 344 4 View
I am looking of the new trend SOM researches. Up to your knowledge, would you suggest some sources or upcoming ideas for SOM development?
11 November 2013 4,934 4 View
I have a large corpus of data and hesitating to create a vocab from frequent words or higher tf-idf valued words. What would be your choice and why?
10 October 2013 8,636 6 View
http://www.image-net.org/download-attributes There is attribute annotated images of imagenet. I expect to use them in my research but being a comparison I am also looking for other stuffs made on...
10 October 2013 4,966 1 View
I am looking for a dataset to test my possible solution for being comparative with the former methods. What dataset could be a great candidate?
10 October 2013 1,794 4 View
I aim to have a large portion of negative instances for my SVM models. However I cannot get any random set to use it as negative since in those sets some instances include those colors as well....
09 September 2013 1,647 3 View
I like Deep Learning concepts and their potential. However the problem is it is not scalable on budget free computation configurations. If we look at all the success stories about Deep Learning,...
09 September 2013 8,911 5 View
I have a lot of data and classes waiting for classification. I have two different ideas in my mind. Use of kernel approximation or high dim. features with linear classifiers. Is there anyone who...
09 September 2013 5,006 2 View
The problem is finding discriminating instances of a dataset to reduce the noise and increase the representatives of the given dataset.
08 August 2013 2,093 1 View
I want to extract salient region from large set of images but as I experienced, some salient region detectors are not fast enough. Is there any good algorithm that is capable of processing images...
08 August 2013 9,995 2 View
I am currently thinking hard about Page Rank and Markov Models for my research problem and I am looking for some answers regarding the stationary distribution of PageRank algorithm. Does it have a...
08 August 2013 2,530 2 View
I know one successful attempt one-class SVM but I'm rather interested in neural approaches over the problem like reconstruction networks or other fundamental neural methods. Are there any other...
08 August 2013 9,834 4 View
I aim to use random walk for ranking of some instances in my dataset by mapping a graph from similarity matrix. On the other hand, I also think that in some way random walk gives the same results...
08 August 2013 1,723 1 View
I have very large dataset and its affinity matrix is dense if I propose to use pagerank therefore the matrix cannot be fitted into memory. I am looking for other variants of successful instance...
08 August 2013 6,977 2 View
Suppose there are bags of unlabeled data and I try to learn the positive instances from those bags. I know there are lots of bag based classification algorithms but my region of interest is...
08 August 2013 8,694 3 View
