Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Amir Mousavinia"'
Publikováno v:
IEEE Access, Vol 8, Pp 145067-145076 (2020)
This paper investigates sensitive minima in popular deep distance learning techniques such as Siamese and Triplet networks. We demonstrate that standard formulations may find solutions that are sensitive to small changes and thus do not generalize we
Externí odkaz:
https://doaj.org/article/19f7eb15c5ae42bbab1404701570408a
Publikováno v:
IEEE Access, 8
IEEE Access, Vol 8, Pp 145067-145076 (2020)
IEEE Access, Vol 8, Pp 145067-145076 (2020)
This paper investigates sensitive minima in popular deep distance learning techniques such as Siamese and Triplet networks. We demonstrate that standard formulations may find solutions that are sensitive to small changes and thus do not generalize we
Publikováno v:
2022 27th International Computer Conference, Computer Society of Iran (CSICC).
Publikováno v:
2022 27th International Computer Conference, Computer Society of Iran (CSICC).
Autor:
Shahab Rajabi, Amir Mousavinia
Publikováno v:
Journal of Control. 13:29-39
Publikováno v:
The Visual Computer. 36:413-424
Conventional geometrical camera calibration algorithms are usually based on running some iterative algorithms on test images obtained carefully from reference objects with precisely known pattern. Providing these test images and running the iterative
Publikováno v:
2021 7th International Conference on Control, Instrumentation and Automation (ICCIA).
This paper’s results are presented on the advantages of employing the sliding mode controller for air-to-fuel ratio (AFR) control over comparisons to the proportional-integral-derivative (PID) controller. The three biggest advantages of this contro
Publikováno v:
2020 International Conference on Machine Vision and Image Processing (MVIP).
Disparity map images, as outputs of a stereo vision system, are known as an effective approach in applications that need depth information in their procedure. One example of such applications is extracting planes with arbitrary attributes from a scen
Autor:
Amir Mousavinia, Hesamodin Hosseinpour
Publikováno v:
Multidimensional Systems and Signal Processing. 30:275-294
The main problems with virtual view synthesis based on the common Depth-Image-Based Rendering (DIBR) algorithms are image rectification, depth map and image de-rectification that lead to additional computational load and image distortion. In this pap
Publikováno v:
IEEE Sensors Journal. 17:3744-3753
Estimation of localization error and selection of system parameters are the key factors in evaluation of visual 3-D systems. Iso-disparity layers and correspondence field are recently introduced to present a graphical model for space sampling in gene