Michael S. Lew
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Michael S. Lew has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Nicu Sebe
University of Trento, Trento, Italy
3 shared publications - Bart Thomee
Yahoo Labs
2 shared publications - Thomas S. Huang
UIUC
2 shared publications - Ard Oerlemans
Google Research, Mountain View, USA
1 shared publication - Ard Oerlemans
Leiden University, Leiden, The Netherlands
1 shared publication - Arif Ghafoor
Purdue University
1 shared publication
Latest Publications
- 14 September 2021
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 10 (3) , 141
Editorial: web of science and scopus impact in IJMIR
- 14 September 2021
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 10 (3) , 141
Editorial: web of science and scopus impact in IJMIR
- 10 May 2021
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 10 (2) , 1-2
Editorial for the ICMR 2020 special issue
- 10 May 2021
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 10 (2) , 1-2
Editorial for the ICMR 2020 special issue
- Open Access
- 10 November 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (4) , 229
State of the journal
- 10 November 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (4) , 229
Open AccessState of the journal
- Open Access
- 16 May 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (2) , 61-62
Special issue on deep learning in image and video retrieval
- 16 May 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (2) , 61-62
Open AccessSpecial issue on deep learning in image and video retrieval
- Open Access
- 9 November 2019
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 8 (4) , 193
State of the journal
- 9 November 2019
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 8 (4) , 193
Open AccessState of the journal
- Open Access
A Comparison of CNN and Classic Features for Image Retrieval
Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input images to score maps and keypoints can be selected with non-maximum suppression. This paper discusses and compares several recent methods that use CNNs for keypoint detection. Experiments are performed both on the CNN based approaches, as well as a selection of conventional methods. In addition to qualitative measures defined on keypoints and descriptors, the bag-of-words (BoW) model is used to implement an image retrieval application, in order to determine how the methods perform in practice. The results show that each type of features are best in different contexts.
Open AccessA Comparison of CNN and Classic Features for Image Retrieval
Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input images to score maps and keypoints can be selected with non-maximum suppression. This paper discusses and compares several recent methods that use CNNs for keypoint detection. Experiments are performed both on the CNN based approaches, as well as a selection of conventional methods. In addition to qualitative measures defined on keypoints and descriptors, the bag-of-words (BoW) model is used to implement an image retrieval application, in order to determine how the methods perform in practice. The results show that each type of features are best in different contexts.
- 19 January 2018
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 7 (1) , 1-2
Editorial for the ICMR 2017 special issue
- 19 January 2018
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 7 (1) , 1-2
Editorial for the ICMR 2017 special issue
- 7 August 2017
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 6 (3) , 189-191
ACM International Conference on Multimedia Retrieval (ICMR): current standing and impact
- 7 August 2017
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 6 (3) , 189-191
ACM International Conference on Multimedia Retrieval (ICMR): current standing and impact
- 25 July 2016
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 5 (3) , 133-134
Top multimedia information retrieval papers
- 25 July 2016
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 5 (3) , 133-134
Top multimedia information retrieval papers
- 7 April 2016
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 5 (2) , 71-72
State of the journal
- 7 April 2016
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 5 (2) , 71-72
State of the journal