Matching Items (105)
Filtering by
- All Subjects: Computer Science
- All Subjects: Image processing--Digital techniques.
- Creators: Li, Baoxin
- Resource Type: Text
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
High-level inference tasks in video applications such as recognition, video retrieval, and zero-shot classification have become an active research area in recent years. One fundamental requirement for such applications is to extract high-quality features that maintain high-level information in the videos.
Many video feature extraction algorithms have been purposed, such as STIP, HOG3D, and Dense Trajectories. These algorithms are often referred to as “handcrafted” features as they were deliberately designed based on some reasonable considerations. However, these algorithms may fail when dealing with high-level tasks or complex scene videos. Due to the success of using deep convolution neural networks (CNNs) to extract global representations for static images, researchers have been using similar techniques to tackle video contents. Typical techniques first extract spatial features by processing raw images using deep convolution architectures designed for static image classifications. Then simple average, concatenation or classifier-based fusion/pooling methods are applied to the extracted features. I argue that features extracted in such ways do not acquire enough representative information since videos, unlike images, should be characterized as a temporal sequence of semantically coherent visual contents and thus need to be represented in a manner considering both semantic and spatio-temporal information.
In this thesis, I propose a novel architecture to learn semantic spatio-temporal embedding for videos to support high-level video analysis. The proposed method encodes video spatial and temporal information separately by employing a deep architecture consisting of two channels of convolutional neural networks (capturing appearance and local motion) followed by their corresponding Fully Connected Gated Recurrent Unit (FC-GRU) encoders for capturing longer-term temporal structure of the CNN features. The resultant spatio-temporal representation (a vector) is used to learn a mapping via a Fully Connected Multilayer Perceptron (FC-MLP) to the word2vec semantic embedding space, leading to a semantic interpretation of the video vector that supports high-level analysis. I evaluate the usefulness and effectiveness of this new video representation by conducting experiments on action recognition, zero-shot video classification, and semantic video retrieval (word-to-video) retrieval, using the UCF101 action recognition dataset.
Many video feature extraction algorithms have been purposed, such as STIP, HOG3D, and Dense Trajectories. These algorithms are often referred to as “handcrafted” features as they were deliberately designed based on some reasonable considerations. However, these algorithms may fail when dealing with high-level tasks or complex scene videos. Due to the success of using deep convolution neural networks (CNNs) to extract global representations for static images, researchers have been using similar techniques to tackle video contents. Typical techniques first extract spatial features by processing raw images using deep convolution architectures designed for static image classifications. Then simple average, concatenation or classifier-based fusion/pooling methods are applied to the extracted features. I argue that features extracted in such ways do not acquire enough representative information since videos, unlike images, should be characterized as a temporal sequence of semantically coherent visual contents and thus need to be represented in a manner considering both semantic and spatio-temporal information.
In this thesis, I propose a novel architecture to learn semantic spatio-temporal embedding for videos to support high-level video analysis. The proposed method encodes video spatial and temporal information separately by employing a deep architecture consisting of two channels of convolutional neural networks (capturing appearance and local motion) followed by their corresponding Fully Connected Gated Recurrent Unit (FC-GRU) encoders for capturing longer-term temporal structure of the CNN features. The resultant spatio-temporal representation (a vector) is used to learn a mapping via a Fully Connected Multilayer Perceptron (FC-MLP) to the word2vec semantic embedding space, leading to a semantic interpretation of the video vector that supports high-level analysis. I evaluate the usefulness and effectiveness of this new video representation by conducting experiments on action recognition, zero-shot video classification, and semantic video retrieval (word-to-video) retrieval, using the UCF101 action recognition dataset.
ContributorsHu, Sheng-Hung (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Liang, Jianming (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2016
Description
In this thesis, I propose a new technique of Aligning English sentence words
with its Semantic Representation using Inductive Logic Programming(ILP). My
work focusses on Abstract Meaning Representation(AMR). AMR is a semantic
formalism to English natural language. It encodes meaning of a sentence in a rooted
graph. This representation has gained attention for its simplicity and expressive power.
An AMR Aligner aligns words in a sentence to nodes(concepts) in its AMR
graph. As AMR annotation has no explicit alignment with words in English sentence,
automatic alignment becomes a requirement for training AMR parsers. The aligner in
this work comprises of two components. First, rules are learnt using ILP that invoke
AMR concepts from sentence-AMR graph pairs in the training data. Second, the
learnt rules are then used to align English sentences with AMR graphs. The technique
is evaluated on publicly available test dataset and the results are comparable with
state-of-the-art aligner.
with its Semantic Representation using Inductive Logic Programming(ILP). My
work focusses on Abstract Meaning Representation(AMR). AMR is a semantic
formalism to English natural language. It encodes meaning of a sentence in a rooted
graph. This representation has gained attention for its simplicity and expressive power.
An AMR Aligner aligns words in a sentence to nodes(concepts) in its AMR
graph. As AMR annotation has no explicit alignment with words in English sentence,
automatic alignment becomes a requirement for training AMR parsers. The aligner in
this work comprises of two components. First, rules are learnt using ILP that invoke
AMR concepts from sentence-AMR graph pairs in the training data. Second, the
learnt rules are then used to align English sentences with AMR graphs. The technique
is evaluated on publicly available test dataset and the results are comparable with
state-of-the-art aligner.
ContributorsAgarwal, Shubham (Author) / Baral, Chitta (Thesis advisor) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2017
Description
With the rise of Online Social Networks (OSN) in the last decade, social network analysis has become a crucial research topic. The OSN graphs have unique properties that distinguish them from other types of graphs. In this thesis, five month Tweet corpus collected from Bangladesh - between June 2016 and October 2016 is analyzed, in order to detect accounts that belong to groups. These groups consist of official and non-official twitter handles of political organizations and NGOs in Bangladesh. A set of network, temporal, spatial and behavioral features are proposed to discriminate between accounts belonging to individual twitter users, news, groups and organization leaders. Finally, the experimental results are presented and a subset of relevant features is identified that lead to a generalizable model. Detection of tiny number of groups from large network is achieved with 0.8 precision, 0.75 recall and 0.77 F1 score. The domain independent network and behavioral features and models developed here are suitable for solving twitter account classification problem in any context.
ContributorsGore, Chinmay Chandrashekhar (Author) / Davulcu, Hasan (Thesis advisor) / Hsiao, Ihan (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2017
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
Description
Compressive sensing theory allows to sense and reconstruct signals/images with lower sampling rate than Nyquist rate. Applications in resource constrained environment stand to benefit from this theory, opening up many possibilities for new applications at the same time. The traditional inference pipeline for computer vision sequence reconstructing the image from compressive measurements. However,the reconstruction process is a computationally expensive step that also provides poor results at high compression rate. There have been several successful attempts to perform inference tasks directly on compressive measurements such as activity recognition. In this thesis, I am interested to tackle a more challenging vision problem - Visual question answering (VQA) without reconstructing the compressive images. I investigate the feasibility of this problem with a series of experiments, and I evaluate proposed methods on a VQA dataset and discuss promising results and direction for future work.
ContributorsHuang, Li-Chin (Author) / Turaga, Pavan (Thesis advisor) / Yang, Yezhou (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2017
Description
Bangladesh is a secular democracy with almost 90% of its population constituting of Muslims and the rest 10% constituting of the minority groups that includes Hindus, Christians, Buddhists, Ahmadi Muslims, Shia, Sufi, LGBT groups and Atheists. In recent years, Bangladesh has experienced an increase in attacks by religious extremist groups, such as IS and AQIS affiliates, hate-groups and politically motivated violence. Attacks have also become indiscriminate, with assailants targeting a wide variety of individuals, including religious minorities and foreigners. According to the telecoms regulator, the number of internet users in Bangladesh now stands at over 66.8 million reaching 41% penetration. Of them, 63 million access the internet through mobile phones. Facebook, with the usage of about 97.2%, is the most used social network in Bangladesh.
In this research, local academics with cultural expertise collaborated to locate and download content from 292 Facebook groups organized under three (3) major umbrella types: Religious Terrorist Violence, Political Intolerance and Issue, and Target-based Intolerance between June2016 - December 2016 period. Dates of real extremist attacks were aligned with corresponding Facebook message streams, identified posts and comments related to the targets and perpetrators of the attacks, and proceeded to use the context of the attacks, their effects, the nature and structure of underlying extremist and counter-violent extremist networks, to study the narratives and trends over time.
In this research, local academics with cultural expertise collaborated to locate and download content from 292 Facebook groups organized under three (3) major umbrella types: Religious Terrorist Violence, Political Intolerance and Issue, and Target-based Intolerance between June2016 - December 2016 period. Dates of real extremist attacks were aligned with corresponding Facebook message streams, identified posts and comments related to the targets and perpetrators of the attacks, and proceeded to use the context of the attacks, their effects, the nature and structure of underlying extremist and counter-violent extremist networks, to study the narratives and trends over time.
ContributorsChhabra, Pankaj (Author) / Davulcu, Hasan (Thesis advisor) / Li, Baoxin (Committee member) / Hsiao, Ihan (Committee member) / Arizona State University (Publisher)
Created2017
Description
Improving accessibility to public buildings by people with special needs has been an important societal commitment that is mandated by federal laws. In the information age, accessibility can mean more than simply providing physical accommodations like ramps for wheel-chairs. Better yet, accessibility will be fundamentally improved, if a user can be made aware of important location-specific information like functions of offices near the user within a building. A smart environment may help a new person quickly get acquainted about the environment. Such features can be more critical for cases of making an indoor environment more accessible to people with visual impairment. With the intention to promote the integration of visually impaired people in society, this thesis efforts on methodologies for building smart and accessible indoor office environments with the help of Apple's Bluetooth Low Energy (BLE) technology called iBeacon to provide location awareness and enable easy access to information about the environment to people with visual impairment. This thesis presents work done on developing an iterative based approach in improving the configuration of given number of iBeacons to gain optimal signal coverage in a given office space environment and enabling smart features such as tagging points of interest and push notifications. This work aims to exploit the idea to look at visual impairment beyond the level of disability and cash it at as an opportunity to bring about a change of style of living. This work develops a methodology by introducing an end-to-end systems that uses intelligent server side and visually-impaired-friendly client side interfaces to give a prototype of an assistive technology to help them do basic activities like getting familiarized about an office environment without the need for asking for assistance.
ContributorsLagisetty, Jashmi (Author) / Li, Baoxin (Thesis advisor) / Hedgpeth, Terri (Committee member) / Balasooriya, Janaka (Committee member) / Arizona State University (Publisher)
Created2017
Description
Answer Set Programming (ASP) is one of the main formalisms in Knowledge Representation (KR) that is being widely applied in a large number of applications. While ASP is effective on Boolean decision problems, it has difficulty in expressing quantitative uncertainty and probability in a natural way.
Logic Programs under the answer set semantics and Markov Logic Network (LPMLN) is a recent extension of answer set programs to overcome the limitation of the deterministic nature of ASP by adopting the log-linear weight scheme of Markov Logic. This thesis investigates the relationships between LPMLN and two other extensions of ASP: weak constraints to express a quantitative preference among answer sets, and P-log to incorporate probabilistic uncertainty. The studied relationships show how different extensions of answer set programs are related to each other, and how they are related to formalisms in Statistical Relational Learning, such as Problog and MLN, which have shown to be closely related to LPMLN. The studied relationships compare the properties of the involved languages and provide ways to compute one language using an implementation of another language.
This thesis first presents a translation of LPMLN into programs with weak constraints. The translation allows for computing the most probable stable models (i.e., MAP estimates) or probability distribution in LPMLN programs using standard ASP solvers so that the well-developed techniques in ASP can be utilized. This result can be extended to other formalisms, such as Markov Logic, ProbLog, and Pearl’s Causal Models, that are shown to be translatable into LPMLN.
This thesis also presents a translation of P-log into LPMLN. The translation tells how probabilistic nonmonotonicity (the ability of the reasoner to change his probabilistic model as a result of new information) of P-log can be represented in LPMLN, which yields a way to compute P-log using standard ASP solvers or MLN solvers.
Logic Programs under the answer set semantics and Markov Logic Network (LPMLN) is a recent extension of answer set programs to overcome the limitation of the deterministic nature of ASP by adopting the log-linear weight scheme of Markov Logic. This thesis investigates the relationships between LPMLN and two other extensions of ASP: weak constraints to express a quantitative preference among answer sets, and P-log to incorporate probabilistic uncertainty. The studied relationships show how different extensions of answer set programs are related to each other, and how they are related to formalisms in Statistical Relational Learning, such as Problog and MLN, which have shown to be closely related to LPMLN. The studied relationships compare the properties of the involved languages and provide ways to compute one language using an implementation of another language.
This thesis first presents a translation of LPMLN into programs with weak constraints. The translation allows for computing the most probable stable models (i.e., MAP estimates) or probability distribution in LPMLN programs using standard ASP solvers so that the well-developed techniques in ASP can be utilized. This result can be extended to other formalisms, such as Markov Logic, ProbLog, and Pearl’s Causal Models, that are shown to be translatable into LPMLN.
This thesis also presents a translation of P-log into LPMLN. The translation tells how probabilistic nonmonotonicity (the ability of the reasoner to change his probabilistic model as a result of new information) of P-log can be represented in LPMLN, which yields a way to compute P-log using standard ASP solvers or MLN solvers.
ContributorsYang, Zhun (Author) / Lee, Joohyung (Thesis advisor) / Baral, Chitta (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2017