Author image not provided
 Mert Dikmen

Add personal information
  Affiliation history
Bibliometrics: publication history
Average citations per article9.29
Citation Count65
Publication count7
Publication years2008-2013
Available for download2
Average downloads per article446.00
Downloads (cumulative)892
Downloads (12 Months)72
Downloads (6 Weeks)12
Arrow RightAuthor only

See all colleagues of this author

See all subject areas


7 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 7 of 7
Sort by:

1 published by ACM
December 2013 ACM Transactions on Architecture and Code Optimization (TACO): Volume 10 Issue 4, December 2013
Publisher: ACM
Citation Count: 2
Downloads (6 Weeks): 1,   Downloads (12 Months): 14,   Downloads (Overall): 286

Full text available: PDFPDF
We optimize a visual object detection application (that uses Vision Video Library kernels) and show that OpenCL is a unified programming paradigm that can provide high performance when running on the Ivy Bridge heterogeneous on-chip architecture. We evaluate different mapping techniques and show that running each kernel where it fits ...
Keywords: Energy efficiency, OpenCL, SIMD, heterogeneous on-chip architectures, portable (mobile) devices

June 2012 CVPR '12: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher: IEEE Computer Society
Citation Count: 1

Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this ...
Keywords: Dictionaries,Histograms,Training,Clustering algorithms,Feature extraction,Object detection,Testing

November 2010 ACCV'10: Proceedings of the 10th Asian conference on Computer vision - Volume Part IV
Publisher: Springer-Verlag
Citation Count: 42

This paper presents a new method for viewpoint invariant pedestrian recognition problem. We use a metric learning framework to obtain a robust metric for large margin nearest neighbor classification with rejection (i.e., classifier will return no matches if all neighbors are beyond a certain distance). The rejection condition necessitates the ...

August 2010 ICPR '10: Proceedings of the 2010 20th International Conference on Pattern Recognition
Publisher: IEEE Computer Society
Citation Count: 0

Classifying images using features extracted from densely sampled local patches has enjoyed significant success in many detection and recognition tasks. It is also well known that generally more than one type of feature is needed to achieve robust classification performance. Previous works using multiple features have addressed this issue either ...
Keywords: Feature fusion, canonical correlations, object detection

January 2010 MMM'10: Proceedings of the 16th international conference on Advances in Multimedia Modeling
Publisher: Springer-Verlag
Citation Count: 1

We investigate the relative strengths of existing space-time interest points in the context of action detection and recognition. The interest point operators evaluated are an extension of the Harris corner detector (Laptev et al. [1]), a space-time Gabor filter (Dollar et al. [2]), and randomized sampling on the motion boundaries. ...

November 2009 ICIP'09: Proceedings of the 16th IEEE international conference on Image processing
Publisher: IEEE Press
Citation Count: 3

We investigate effective means of building robust dictionaries for detecting the sparse foreground in videos with static background. This work is an extension to our existing solution [1] to foreground/background segmentation problem using the linear programming method [2] proposed to detect sparse errors in signals, which are created by a ...
Keywords: background subtraction

7 published by ACM
October 2008 MM '08: Proceedings of the 16th ACM international conference on Multimedia
Publisher: ACM
Citation Count: 16
Downloads (6 Weeks): 11,   Downloads (12 Months): 58,   Downloads (Overall): 606

Full text available: PDFPDF
This paper studies the problem of recognizing gender from full body images. This problem has not been addressed before, partly because of the variant nature of human bodies and clothing that can bring tough difficulties. However, gender recognition has high application potentials, e.g. security surveillance and customer statistics collection in ...
Keywords: gender recognition, human body

The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us