Matching Items (83)
Filtering by
- Genre: Doctoral Dissertation
- Creators: Li, Baoxin
Description
Mixture of experts is a machine learning ensemble approach that consists of individual models that are trained to be ``experts'' on subsets of the data, and a gating network that provides weights to output a combination of the expert predictions. Mixture of experts models do not currently see wide use due to difficulty in training diverse experts and high computational requirements. This work presents modifications of the mixture of experts formulation that use domain knowledge to improve training, and incorporate parameter sharing among experts to reduce computational requirements.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
ContributorsDodge, Samuel Fuller (Author) / Karam, Lina (Thesis advisor) / Jayasuriya, Suren (Committee member) / Li, Baoxin (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2018
Description
Computer vision technology automatically extracts high level, meaningful information from visual data such as images or videos, and the object recognition and detection algorithms are essential in most computer vision applications. In this dissertation, we focus on developing algorithms used for real life computer vision applications, presenting innovative algorithms for object segmentation and feature extraction for objects and actions recognition in video data, and sparse feature selection algorithms for medical image analysis, as well as automated feature extraction using convolutional neural network for blood cancer grading.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
ContributorsCao, Jun (Author) / Li, Baoxin (Thesis advisor) / Liu, Huan (Committee member) / Zhang, Yu (Committee member) / Zhang, Junshan (Committee member) / Arizona State University (Publisher)
Created2018
Description
Recognizing that CEOs are less capable of diversifying their employment risks than shareholders who could diversify their investment risks through portfolio investments, agency theory assumes that CEOs tend to be risk averse compared with shareholders. Based on this assumption, agency theory scholars suggest that to align the risk preference of CEOs with that of shareholders, CEOs need to be closely monitored and have less power. SEC regulators have been adopting the suggestion and accordingly CEO power has been reduced in the past decades. However, the empirical results are mixed and cannot provide solid support for the suggestion that reducing CEO power could lead the CEO to take more risks.
Considering that managerial risk taking is an important issue in strategic management research and agency theory has been widely adopted in academia and business worlds, it is imperative to clarify the mechanism behind the relationship between CEO power and risk taking. My study aims to fill this research gap. In this study I follow agency theory to take an employment security perspective and fully consider how CEOs’ concern about employment security is affected by their power and ownership structure to enrich the understanding of the effects of CEO power and ownership structure on risk taking. I fine-tune the key concept CEO power into the CEO power over board and introduce a key aspect of ownership structure - nontransient investor ownership. I further suggest that CEO power over board and nontransient investor ownership affect CEOs’ employment security and the resulting CEO risk taking. In addition, I consider a set of industry and firm characteristics as the boundary conditions for the effects of CEO power and nontransient investor ownership on CEO risk-taking. This set of industry and firm characteristics include industry complexity, industry dynamism, industry munificence and firm slack.
I test my theory using a large-scale, multi-year sample of U.S. publicly listed S&P 1500 firms between 2001 and 2017. My main hypotheses about the effects of CEO power over board and nontransient investor ownership on CEO risk taking receive strong support.
Considering that managerial risk taking is an important issue in strategic management research and agency theory has been widely adopted in academia and business worlds, it is imperative to clarify the mechanism behind the relationship between CEO power and risk taking. My study aims to fill this research gap. In this study I follow agency theory to take an employment security perspective and fully consider how CEOs’ concern about employment security is affected by their power and ownership structure to enrich the understanding of the effects of CEO power and ownership structure on risk taking. I fine-tune the key concept CEO power into the CEO power over board and introduce a key aspect of ownership structure - nontransient investor ownership. I further suggest that CEO power over board and nontransient investor ownership affect CEOs’ employment security and the resulting CEO risk taking. In addition, I consider a set of industry and firm characteristics as the boundary conditions for the effects of CEO power and nontransient investor ownership on CEO risk-taking. This set of industry and firm characteristics include industry complexity, industry dynamism, industry munificence and firm slack.
I test my theory using a large-scale, multi-year sample of U.S. publicly listed S&P 1500 firms between 2001 and 2017. My main hypotheses about the effects of CEO power over board and nontransient investor ownership on CEO risk taking receive strong support.
ContributorsZhu, Qi (Author) / Shen, Wei (Thesis advisor) / Zhu, David (Thesis advisor) / Certo, Trevis (Committee member) / Arizona State University (Publisher)
Created2019
Description
Visual processing in social media platforms is a key step in gathering and understanding information in the era of Internet and big data. Online data is rich in content, but its processing faces many challenges including: varying scales for objects of interest, unreliable and/or missing labels, the inadequacy of single modal data and difficulty in analyzing high dimensional data. Towards facilitating the processing and understanding of online data, this dissertation primarily focuses on three challenges that I feel are of great practical importance: handling scale differences in computer vision tasks, such as facial component detection and face retrieval, developing efficient classifiers using partially labeled data and noisy data, and employing multi-modal models and feature selection to improve multi-view data analysis. For the first challenge, I propose a scale-insensitive algorithm to expedite and accurately detect facial landmarks. For the second challenge, I propose two algorithms that can be used to learn from partially labeled data and noisy data respectively. For the third challenge, I propose a new framework that incorporates feature selection modules into LDA models.
ContributorsZhou, Xu (Author) / Li, Baoxin (Thesis advisor) / Hsiao, Sharon (Committee member) / Davulcu, Hasan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2018
Description
Information forensics and security have come a long way in just a few years thanks to the recent advances in biometric recognition. The main challenge remains a proper design of a biometric modality that can be resilient to unconstrained conditions, such as quality distortions. This work presents a solution to face and ear recognition under unconstrained visual variations, with a main focus on recognition in the presence of blur, occlusion and additive noise distortions.
First, the dissertation addresses the problem of scene variations in the presence of blur, occlusion and additive noise distortions resulting from capture, processing and transmission. Despite their excellent performance, ’deep’ methods are susceptible to visual distortions, which significantly reduce their performance. Sparse representations, on the other hand, have shown huge potential capabilities in handling problems, such as occlusion and corruption. In this work, an augmented SRC (ASRC) framework is presented to improve the performance of the Spare Representation Classifier (SRC) in the presence of blur, additive noise and block occlusion, while preserving its robustness to scene dependent variations. Different feature types are considered in the performance evaluation including image raw pixels, HoG and deep learning VGG-Face. The proposed ASRC framework is shown to outperform the conventional SRC in terms of recognition accuracy, in addition to other existing sparse-based methods and blur invariant methods at medium to high levels of distortion, when particularly used with discriminative features.
In order to assess the quality of features in improving both the sparsity of the representation and the classification accuracy, a feature sparse coding and classification index (FSCCI) is proposed and used for feature ranking and selection within both the SRC and ASRC frameworks.
The second part of the dissertation presents a method for unconstrained ear recognition using deep learning features. The unconstrained ear recognition is performed using transfer learning with deep neural networks (DNNs) as a feature extractor followed by a shallow classifier. Data augmentation is used to improve the recognition performance by augmenting the training dataset with image transformations. The recognition performance of the feature extraction models is compared with an ensemble of fine-tuned networks. The results show that, in the case where long training time is not desirable or a large amount of data is not available, the features from pre-trained DNNs can be used with a shallow classifier to give a comparable recognition accuracy to the fine-tuned networks.
First, the dissertation addresses the problem of scene variations in the presence of blur, occlusion and additive noise distortions resulting from capture, processing and transmission. Despite their excellent performance, ’deep’ methods are susceptible to visual distortions, which significantly reduce their performance. Sparse representations, on the other hand, have shown huge potential capabilities in handling problems, such as occlusion and corruption. In this work, an augmented SRC (ASRC) framework is presented to improve the performance of the Spare Representation Classifier (SRC) in the presence of blur, additive noise and block occlusion, while preserving its robustness to scene dependent variations. Different feature types are considered in the performance evaluation including image raw pixels, HoG and deep learning VGG-Face. The proposed ASRC framework is shown to outperform the conventional SRC in terms of recognition accuracy, in addition to other existing sparse-based methods and blur invariant methods at medium to high levels of distortion, when particularly used with discriminative features.
In order to assess the quality of features in improving both the sparsity of the representation and the classification accuracy, a feature sparse coding and classification index (FSCCI) is proposed and used for feature ranking and selection within both the SRC and ASRC frameworks.
The second part of the dissertation presents a method for unconstrained ear recognition using deep learning features. The unconstrained ear recognition is performed using transfer learning with deep neural networks (DNNs) as a feature extractor followed by a shallow classifier. Data augmentation is used to improve the recognition performance by augmenting the training dataset with image transformations. The recognition performance of the feature extraction models is compared with an ensemble of fine-tuned networks. The results show that, in the case where long training time is not desirable or a large amount of data is not available, the features from pre-trained DNNs can be used with a shallow classifier to give a comparable recognition accuracy to the fine-tuned networks.
ContributorsMounsef, Jinane (Author) / Karam, Lina (Thesis advisor) / Papandreou-Suppapola, Antonia (Committee member) / Li, Baoxin (Committee member) / Ren, Fengbo (Committee member) / Arizona State University (Publisher)
Created2018
Description
As people age, the desire to grow old independently and in place becomes larger and takes greater importance in their lives. Successful aging involves the physical, mental and social well-being of an individual. To enable successful aging of older adults, it is necessary for them to perform both activities of daily living (ADL) and instrumental activities of daily living (IADL). Embedded assessment has made it possible to assess an individual's functional ability in-place, however the success of any technology depends largely on the user than the technology itself. Previous researches in in-situ functional assessment systems have heavily focused on the technology rather than on the user. This dissertation takes a user-centric approach to this problem by trying to identify the design and technical challenges of deploying and using a functional assessment system in the real world.
To investigate this line of research, a case study was conducted with 4 older adults in their homes, interviews were conducted with 8 caregivers and a controlled lab experiment was conducted with 8 young healthy adults at ASU, to test the sensors. This methodology provides a significant opportunity to advance the scientific field by expanding the present focus on IADL task performance to an integrated assessment of ADL and IADL task performance. Doing so would not only be more effective in identifying functional decline but could also provide a more comprehensive assessment of individuals' functional abilities with independence and also providing the caregivers with much needed respite.
The controlled lab study tested the sensors embedded into daily objects and found them to be reliable, and efficient. Short term exploratory case studies with healthy older adults revealed the challenges associated with design and technical aspects of the current system, while inductive analysis performed on interviews with caregivers helped to generate central themes on which future functional assessment systems need to be designed and built. The key central themes were a) focus on design / user experience, b) consider user's characteristics, personality, behavior and functional ability, c) provide support for independence, and d) adapt to individual user's needs.
To investigate this line of research, a case study was conducted with 4 older adults in their homes, interviews were conducted with 8 caregivers and a controlled lab experiment was conducted with 8 young healthy adults at ASU, to test the sensors. This methodology provides a significant opportunity to advance the scientific field by expanding the present focus on IADL task performance to an integrated assessment of ADL and IADL task performance. Doing so would not only be more effective in identifying functional decline but could also provide a more comprehensive assessment of individuals' functional abilities with independence and also providing the caregivers with much needed respite.
The controlled lab study tested the sensors embedded into daily objects and found them to be reliable, and efficient. Short term exploratory case studies with healthy older adults revealed the challenges associated with design and technical aspects of the current system, while inductive analysis performed on interviews with caregivers helped to generate central themes on which future functional assessment systems need to be designed and built. The key central themes were a) focus on design / user experience, b) consider user's characteristics, personality, behavior and functional ability, c) provide support for independence, and d) adapt to individual user's needs.
ContributorsRavishankar, Vijay Kumar (Author) / Burleson, Winslow (Thesis advisor) / Coon, David (Committee member) / Mahoney, Diane (Committee member) / Walker, Erin (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2015
Description
Online health forums provide a convenient channel for patients, caregivers, and medical professionals to share their experience, support and encourage each other, and form health communities. The fast growing content in health forums provides a large repository for people to seek valuable information. A forum user can issue a keyword query to search health forums regarding to some specific questions, e.g., what treatments are effective for a disease symptom? A medical researcher can discover medical knowledge in a timely and large-scale fashion by automatically aggregating the latest evidences emerging in health forums.
This dissertation studies how to effectively discover information in health forums. Several challenges have been identified. First, the existing work relies on the syntactic information unit, such as a sentence, a post, or a thread, to bind different pieces of information in a forum. However, most of information discovery tasks should be based on the semantic information unit, a patient. For instance, given a keyword query that involves the relationship between a treatment and side effects, it is expected that the matched keywords refer to the same patient. In this work, patient-centered mining is proposed to mine patient semantic information units. In a patient information unit, the health information, such as diseases, symptoms, treatments, effects, and etc., is connected by the corresponding patient.
Second, the information published in health forums has varying degree of quality. Some information includes patient-reported personal health experience, while others can be hearsay. In this work, a context-aware experience extraction framework is proposed to mine patient-reported personal health experience, which can be used for evidence-based knowledge discovery or finding patients with similar experience.
At last, the proposed patient-centered and experience-aware mining framework is used to build a patient health information database for effectively discovering adverse drug reactions (ADRs) from health forums. ADRs have become a serious health problem and even a leading cause of death in the United States. Health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. Empirical evaluation shows the effectiveness of the proposed approach.
This dissertation studies how to effectively discover information in health forums. Several challenges have been identified. First, the existing work relies on the syntactic information unit, such as a sentence, a post, or a thread, to bind different pieces of information in a forum. However, most of information discovery tasks should be based on the semantic information unit, a patient. For instance, given a keyword query that involves the relationship between a treatment and side effects, it is expected that the matched keywords refer to the same patient. In this work, patient-centered mining is proposed to mine patient semantic information units. In a patient information unit, the health information, such as diseases, symptoms, treatments, effects, and etc., is connected by the corresponding patient.
Second, the information published in health forums has varying degree of quality. Some information includes patient-reported personal health experience, while others can be hearsay. In this work, a context-aware experience extraction framework is proposed to mine patient-reported personal health experience, which can be used for evidence-based knowledge discovery or finding patients with similar experience.
At last, the proposed patient-centered and experience-aware mining framework is used to build a patient health information database for effectively discovering adverse drug reactions (ADRs) from health forums. ADRs have become a serious health problem and even a leading cause of death in the United States. Health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. Empirical evaluation shows the effectiveness of the proposed approach.
ContributorsLiu, Yunzhong (Author) / Chen, Yi (Thesis advisor) / Liu, Huan (Thesis advisor) / Li, Baoxin (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2016
Description
The rapid growth of social media in recent years provides a large amount of user-generated visual objects, e.g., images and videos. Advanced semantic understanding approaches on such visual objects are desired to better serve applications such as human-machine interaction, image retrieval, etc. Semantic visual attributes have been proposed and utilized in multiple visual computing tasks to bridge the so-called "semantic gap" between extractable low-level feature representations and high-level semantic understanding of the visual objects.
Despite years of research, there are still some unsolved problems on semantic attribute learning. First, real-world applications usually involve hundreds of attributes which requires great effort to acquire sufficient amount of labeled data for model learning. Second, existing attribute learning work for visual objects focuses primarily on images, with semantic analysis on videos left largely unexplored.
In this dissertation I conduct innovative research and propose novel approaches to tackling the aforementioned problems. In particular, I propose robust and accurate learning frameworks on both attribute ranking and prediction by exploring the correlation among multiple attributes and utilizing various types of label information. Furthermore, I propose a video-based skill coaching framework by extending attribute learning to the video domain for robust motion skill analysis. Experiments on various types of applications and datasets and comparisons with multiple state-of-the-art baseline approaches confirm that my proposed approaches can achieve significant performance improvements for the general attribute learning problem.
Despite years of research, there are still some unsolved problems on semantic attribute learning. First, real-world applications usually involve hundreds of attributes which requires great effort to acquire sufficient amount of labeled data for model learning. Second, existing attribute learning work for visual objects focuses primarily on images, with semantic analysis on videos left largely unexplored.
In this dissertation I conduct innovative research and propose novel approaches to tackling the aforementioned problems. In particular, I propose robust and accurate learning frameworks on both attribute ranking and prediction by exploring the correlation among multiple attributes and utilizing various types of label information. Furthermore, I propose a video-based skill coaching framework by extending attribute learning to the video domain for robust motion skill analysis. Experiments on various types of applications and datasets and comparisons with multiple state-of-the-art baseline approaches confirm that my proposed approaches can achieve significant performance improvements for the general attribute learning problem.
ContributorsChen, Lin (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2016
Description
A lot of strides have been made in enabling technologies to aid individuals with visual impairment live an independent life. The advent of smart devices and participatory web has especially facilitated the possibility of new interactions to aide everyday tasks. Current systems however tend to be complex and require multiple cumbersome devices which invariably come with steep learning curves. Building new cyber-human systems with simple integrated interfaces while keeping in mind the specific requirements of the target users would help alleviate their mundane yet significant daily needs. Navigation is one such significant need that forms an integral part of everyday life and is one of the areas where individuals with visual impairment face the most discomfort. There is little technology out there to help travelers with navigating new routes. A number of research prototypes have been proposed but none of them are available to the general population. This may be due to the need for special equipment that needs expertise before deployment, or trained professionals needing to calibrate devices or because of the fact that the systems are just not scalable. Another area that needs assistance is the field of education. Lot of the classroom material and textbook material is not readily available in alternate formats for use. Another such area that requires attention is information delivery in the age of web 2.0. Popular websites like Facebook, Amazon, etc are designed with sighted people as target audience. While the mobile editions with their pared down versions make it easier to navigate with screen readers, the truth remains that there is still a long way to go in making such websites truly accessible.
ContributorsPaladugu, Devi Archana (Author) / Li, Baoxin (Thesis advisor) / Hedgpeth, Terri (Committee member) / Atkinson, Robert (Committee member) / Walker, Erin (Committee member) / Arizona State University (Publisher)
Created2016
Description
Visual Question Answering (VQA) is a new research area involving technologies ranging from computer vision, natural language processing, to other sub-fields of artificial intelligence such as knowledge representation. The fundamental task is to take as input one image and one question (in text) related to the given image, and to generate a textual answer to the input question. There are two key research problems in VQA: image understanding and the question answering. My research mainly focuses on developing solutions to support solving these two problems.
In image understanding, one important research area is semantic segmentation, which takes images as input and output the label of each pixel. As much manual work is needed to label a useful training set, typical training sets for such supervised approaches are always small. There are also approaches with relaxed labeling requirement, called weakly supervised semantic segmentation, where only image-level labels are needed. With the development of social media, there are more and more user-uploaded images available
on-line. Such user-generated content often comes with labels like tags and may be coarsely labelled by various tools. To use these information for computer vision tasks, I propose a new graphic model by considering the neighborhood information and their interactions to obtain the pixel-level labels of the images with only incomplete image-level labels. The method was evaluated on both synthetic and real images.
In question answering, my research centers on best answer prediction, which addressed two main research topics: feature design and model construction. In the feature design part, most existing work discussed how to design effective features for answer quality / best answer prediction. However, little work mentioned how to design features by considering the relationship between answers of one given question. To fill this research gap, I designed new features to help improve the prediction performance. In the modeling part, to employ the structure of the feature space, I proposed an innovative learning-to-rank model by considering the hierarchical lasso. Experiments with comparison with the state-of-the-art in the best answer prediction literature have confirmed
that the proposed methods are effective and suitable for solving the research task.
In image understanding, one important research area is semantic segmentation, which takes images as input and output the label of each pixel. As much manual work is needed to label a useful training set, typical training sets for such supervised approaches are always small. There are also approaches with relaxed labeling requirement, called weakly supervised semantic segmentation, where only image-level labels are needed. With the development of social media, there are more and more user-uploaded images available
on-line. Such user-generated content often comes with labels like tags and may be coarsely labelled by various tools. To use these information for computer vision tasks, I propose a new graphic model by considering the neighborhood information and their interactions to obtain the pixel-level labels of the images with only incomplete image-level labels. The method was evaluated on both synthetic and real images.
In question answering, my research centers on best answer prediction, which addressed two main research topics: feature design and model construction. In the feature design part, most existing work discussed how to design effective features for answer quality / best answer prediction. However, little work mentioned how to design features by considering the relationship between answers of one given question. To fill this research gap, I designed new features to help improve the prediction performance. In the modeling part, to employ the structure of the feature space, I proposed an innovative learning-to-rank model by considering the hierarchical lasso. Experiments with comparison with the state-of-the-art in the best answer prediction literature have confirmed
that the proposed methods are effective and suitable for solving the research task.
ContributorsTian, Qiongjie (Author) / Li, Baoxin (Thesis advisor) / Tong, Hanghang (Committee member) / Davulcu, Hasan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2017