Browsing by Subject "Multiple features"

Now showing 1 - 4 of 4

Open Access
Multi-channel TDMA scheduling in wireless sensor networks
(2013) Uyanık, Özge
The Multiple Instance Learning (MIL) paradigm arises to be useful in many application domains, whereas it is particularly suitable for computer vision problems due to the difficulty of obtaining manual labeling. Multiple Instance Learning methods have large applicability to a variety of challenging learning problems in computer vision, including object recognition and detection, tracking, image classification, scene classification and more. As opposed to working with single instances as in standard supervised learning, Multiple Instance Learning operates over bags of instances. A bag is labeled as positive if it is known to contain at least one positive instance; otherwise it is labeled as negative. The overall learning task is to learn a model for some concept using a training set that is formed of bags. A vital component of using Multiple Instance Learning in computer vision is its design for abstracting the visual problem to multi-instance representation, which involves determining what the bag is and what are the instances in the bag. In this context, we consider three different computer vision problems and propose solutions for each of them via novel representations. The first problem is image retrieval and re-ranking; we propose a method that automatically constructs multiple candidate Multi-instance bags, which are likely to contain relevant images. The second problem we look into is recognizing actions from still images, where we extract several candidate object regions and approach the problem of identifying related objects from a weakly supervised point of view. Finally, we address the recognition of human interactions in videos within a MIL framework. In human interaction recognition, videos may be composed of frames of different activities, and the task is to identify the interaction in spite of irrelevant activities that are scattered through the video. To overcome this problem, we use the idea of Multiple Instance Learning to tackle irrelevant actions in the whole video sequence classification. Each of the outlined problems are tested on benchmark datasets of the problems and compared with the state-of-the-art. The experimental results verify the advantages of the proposed MIL approaches to these vision problems.
Open Access
On recognizing actions in still images via multiple features
(Springer, Berlin, Heidelberg, 2012) Şener, Fadime; Bas, C.; Ikizler-Cinbis, N.
We propose a multi-cue based approach for recognizing human actions in still images, where relevant object regions are discovered and utilized in a weakly supervised manner. Our approach does not require any explicitly trained object detector or part/attribute annotation. Instead, a multiple instance learning approach is used over sets of object hypotheses in order to represent objects relevant to the actions. We test our method on the extensive Stanford 40 Actions dataset [1] and achieve significant performance gain compared to the state-of-the-art. Our results show that using multiple object hypotheses within multiple instance learning is effective for human action recognition in still images and such an object representation is suitable for using in conjunction with other visual features. © 2012 Springer-Verlag.
Open Access
Theoretical and spectroscopic investigations on the structure and bonding in B-C-N thin films
(2009) Bengu, E.; Genisel, M. F.; Gulseren, O.; Ovali, R.
In this study, we have synthesized boron, carbon, and nitrogen containing films using RF sputter deposition. We investigated the effects of deposition parameters on the chemical environment of boron, carbon, and nitrogen atoms inside the films. Techniques used for this purpose were grazing incidence reflectance-Fourier-transform infrared spectroscopy (GIR-FTIR), X-ray photoelectron spectroscopy (XPS), transmission electron microscopy (TEM) and electron energy loss spectroscopy (EELS). GIR-FTIR experiments on the B-C-N films deposited indicated presence of multiple features in the 600 to 1700 cm- 1 range for the infrared (IR) spectra. Analysis of the IR spectra, XPS and the corresponding EELS data from the films has been done in a collective manner. The results from this study suggested even under nitrogen rich synthesis conditions carbon atoms in the B-C-N films prefer to be surrounded by other carbon atoms rather than boron and/or nitrogen. Furthermore, we have observed a similar behavior in the chemistry of B-C-N films deposited with increasing substrate bias conditions. In order to better understand these results, we have compared and evaluated the relative stability of various nearest-neighbor and structural configurations of carbon atoms in a single BN sheet using DFT calculations. These calculations also indicated that structures and configurations that increase the relative amount of C-C bonding with respect to B-C and/or C-N were energetically favorable than otherwise. As a conclusion, carbon tends to phase-segregate in to carbon clusters rather than displaying a homogeneous distribution for the films deposited in this study under the deposition conditions studied.
Open Access
Utilizing multiple instance learning for computer vision tasks
(2013) Şener, Fadime
The Multiple Instance Learning (MIL) paradigm arises to be useful in many application domains, whereas it is particularly suitable for computer vision problems due to the difficulty of obtaining manual labeling. Multiple Instance Learning methods have large applicability to a variety of challenging learning problems in computer vision, including object recognition and detection, tracking, image classification, scene classification and more. As opposed to working with single instances as in standard supervised learning, Multiple Instance Learning operates over bags of instances. A bag is labeled as positive if it is known to contain at least one positive instance; otherwise it is labeled as negative. The overall learning task is to learn a model for some concept using a training set that is formed of bags. A vital component of using Multiple Instance Learning in computer vision is its design for abstracting the visual problem to multi-instance representation, which involves determining what the bag is and what are the instances in the bag. In this context, we consider three different computer vision problems and propose solutions for each of them via novel representations. The first problem is image retrieval and re-ranking; we propose a method that automatically constructs multiple candidate Multi-instance bags, which are likely to contain relevant images. The second problem we look into is recognizing actions from still images, where we extract several candidate object regions and approach the problem of identifying related objects from a weakly supervised point of view. Finally, we address the recognition of human interactions in videos within a MIL framework. In human interaction recognition, videos may be composed of frames of different activities, and the task is to identify the interaction in spite of irrelevant activities that are scattered through the video. To overcome this problem, we use the idea of Multiple Instance Learning to tackle irrelevant actions in the whole video sequence classification. Each of the outlined problems are tested on benchmark datasets of the problems and compared with the state-of-the-art. The experimental results verify the advantages of the proposed MIL approaches to these vision problems.