This work focuses on two problems in machine translation: lexical choice and target-side morphology. The first problem is the correct transfer of meaning from the source language to the target language. The second problem, which is mainly relevant for morphologically rich target languages, is then the choice of the correct surface form of each target lexeme. We work with these problems within the framework of phrase-based machine translation and we propose a discriminative model of translation which utilizes both source and target context information and which uses rich linguistically motivated features. We show how our model addresses specific weaknesses of standard phrase-based systems and that it provides consistent improvements of translation quality across a broad range of experiments. Apart from our main contribution, we also provide a number of experimental evaluations, analyses and manual annotation experiments, mostly related to English-Czech translation.

Visual tracking concerns the problem of following an arbitrary object in a video sequence. In this thesis, we examine how to use stereo images to extend existing visual tracking algorithms, which methods exists to obtain information from stereo images, and how the results change as the parameters to each tracker vary. For this purpose, four abstract approaches are identified, with five distinct implementations. Each tracker implementation is an extension of a baseline algorithm, MOSSE. The free parameters of each model are optimized with respect to two different evaluation strategies called nor- and wir-tests, and four different objective functions, which are then fixed when comparing the models against each other. The results are created on single target tracks extracted from the KITTI tracking dataset, and the optimization results show that none of the objective functions are sensitive to the exposed parameters under the joint selection of model and dataset. The evaluation results also shows that none of the extensions improve the results of the baseline tracker.

The purpose of this study was to assess if Behavioral Skills Training (BST) can be used to train a sticker to function as a discriminative stimulus (Sᴰ) for engaging in household poison safety skills and assess whether this skill generalized to untrained household chemicals that bear the Sᴰ in the form of a sticker. Three typically developing children ages 3 and 5 and their parents participated in this study which took place in their homes. BST effectively taught children to engage in household poison safety skills when they come into contact with the trained household poison(s) labeled with the sticker Sᴰ and this skill generalized to novel household poisons that were also labeled with the sticker Sᴰ; however, some additional BST was required in two cases.

Visual Object Tracking is the computer vision problem of estimating a target trajectory in a video given only its initial state. A visual tracker often acts as a component in the intelligent vision systems seen in for instance surveillance, autonomous vehicles or robots, and unmanned aerial vehicles. Applications may require robust tracking performance on difficult sequences depicting targets undergoing large changes in appearance, while enforcing a real-time constraint. Discriminative correlation filters have shown promising tracking performance in recent years, and consistently improved state-of-the-art. With the advent of deep learning, new robust deep features have improved tracking performance considerably. However, methods based on discriminative correlation filters learn a rigid template describing the target appearance. This implies an assumption of target rigidity which is not fulfilled in practice. This thesis introduces an approach which integrates deformability into a stateof-the-art tracker. The approach is thoroughly tested on three challenging visual tracking benchmarks, achieving state-of-the-art performance.

京都大学 / 0048 / 新制・課程博士 / 博士(社会健康医学) / 甲第22044号 / 社医博第97号 / 新制||社医||10(附属図書館) / 京都大学大学院医学研究科社会健康医学系専攻 / (主査)教授 川上 浩司, 教授 福原 俊一, 教授 小池 薫 / 学位規則第4条第1項該当 / Doctor of Public Health / Kyoto University / DFAM

Generic visual object tracking is the task of tracking one or several objects in all frames in a video, knowing only the location and size of the target in the initial frame. Visual tracking can be carried out in both the infrared and the visual spectrum simultaneously, this is known as multi-modal tracking. Utilizing both spectra can result in a more diverse tracker since visual tracking in infrared imagery makes it possible to detect objects even in poor visibility or in complete darkness. However, infrared imagery lacks the number of details that are present in visual images. A common method for visual tracking is to use discriminative correlation filters (DCF). These correlation filters are then used to detect an object in every frame of an image sequence. This thesis focuses on investigating aspects of a DCF based tracker, operating in the two different modalities, infrared and visual imagery. First, it was investigated whether the tracking benefits from using two channels instead of one and what happens to the tracking result if one of those channels is degraded by an external cause. It was also investigated if the addition of image features can further improve the tracking. The result shows that the tracking improves when using two channels instead of only using a single channel. It also shows that utilizing two channels is a good way to create a robust tracker, which is still able to perform even though one of the channels is degraded. Using deep features, extracted from a pre-trained convolutional neural network, was the image feature improving the tracking the most, although the implementation of the deep features made the tracking significantly slower.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第18482号 / 情博第533号 / 新制||情||94(附属図書館) / 31360 / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 美濃 導彦, 教授 河原 達也, 教授 中村 裕一 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Anorexia Nervosa (AN) is a severe and complex psychiatric disorder characterized by significantly low body weight, an intense fear of gaining weight, and a distorted body image. Despite otherwise successful treatments, body image distortions are often persistent and are considered a critical factor in the persistence, development, and relapse of AN. The present review outlines the current literature on tactile distance processing in AN to investigate and discuss its proposed role in the persistence and development of a distorted body image. The discussion of literature further discusses its implications for cognitive neuroscience since AN patients display similar symptoms as patients diagnosed with body image-related neuropsychiatric disorders with damage to the parietal lobe. The evidence suggests that individuals with AN have poorer tactile distance estimation than controls but do not differ regarding tactile detection. This review outlines the current literature, identifies gaps within the methodology, and proposes novel directions for future research.

This thesis examines motivation in English L1 learners of Japanese as a Foreign Language (JFL) by analyzing the students' responses to a questionnaire modeled after Dörnyei's research and an observational instrument called the Motivation Behaviors of Language Learning (MBLL) modeled after Guilloteaux and Dörnyei's (2008) research on motivational teaching strategies on behaviors. The data from the questionnaires were subjected to a discriminative analysis of students answers in relation to a high grade (receiving a B- or higher) or lower (C+ or lower) in their Japanese classes. A Factor Analysis of the data was also carried out. The discriminative results could predict students' receiving higher or lower grades with 13-16% error. In addition, behaviors examined in the 200-level Japanese classes seemed to match students' responses to a questionnaire, suggesting they are not highly motivated. However, students who passed this class reported similar study habits outside of class in preparation as students from a 400-level class. The Factor Analysis also found that students with higher self-perception of their motivation and language aptitude tended to receive higher grades in the class. The results suggest that motivation can be further understood by understanding behaviors in addition to traditional questionnaires, and students' self perceptions of their language abilities may affect their grades in the language classroom. In the future, motivation research should include triangulating questionnaire data with other data, such as observational instruments. This thesis is a step in that direction.

No description available.