This thesis addresses the problem of temporal action segmentation in videos, where the goal is to label every video frame with the appropriate action class present. We focus on the domain of NFL football videos, where action classes represent common football play types. For action segmentation, we use a temporal...
Alignment of genomic sequences from different species is becoming an increasingly powerful method in biology, and is being used for many purposes. The result of sequence alignments is a list of pairs of matched locations between the pattern string and the text string. However, without any proper visualization tools to...
In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
Significance: Movement intent decoding algorithms can interpret human bioelectrical signals to control prosthetic limbs with many degrees of freedom (DOFs). This work involves decoding volitional movement intent from surface electromyogram (sEMG) signals to control prosthetic arms. To train these algorithms, patients flex their muscles to “follow” a movement prompt, and...
Humans are remarkably efficient in learning by interacting with other people and observing their behavior. Children learn by watching their parents’ actions and mimic their behavior. When they are not sure about their parents demonstration, they communicate with them, ask questions, and learn from their feedback. On the other hand,...
Knowledge workers are struggling in the information flood. There is a growing interest in intelligent desktop environments that help knowledge workers organize their daily life. Intelligent desktop environments allow the desktop user to define a set of “activities” that characterize the user’s desktop work. These environments then attempt to identify...
Partial programming is a field of study where users specify an outline or skeleton of a program, but leave various parts undefined. The undefined parts are then completed by an external mechanism to form a complete program. Adaptation-Based Programming (ABP) is a method of partial programming that utilizes techniques from...
Movement intent decoders, which interpret volitional movement intent from human bioelectric signals, can be incorporated into modern neuroprostheses to offer people living with limb loss or paralysis the potential to regain their lost motor control. Machine learning methods have become the research standard for continuous decoders with high degrees of...
Robotic Bipedal locomotion holds the potential for efficient, robust traversal of difficult terrain. The difficulty lies in the dynamics of locomotion which complicate control and motion planning. Bipedal locomotion dynamics are dimensionally large problems, extremely nonlinear, and operate on the limits of actuator capabilities, which limit the performance of generic...
As bipedal robots move ever closer to being integrated into all manner of real world envi-ronments there is a necessity to push their dynamic capabilities to meet or exceed those of humans and animals. Advancements must be made to address ordinary challenges that arise everyday in the same environments that...
A fundamental problem in computer vision is to partition an image into meaningful segments. While image segmentation is required by many applications, the thesis focuses on segmentation of computed tomography (CT) images for analysis and quality control of composite materials. The key research contribution of this thesis is a novel...
Advances in sensor technology are greatly expanding the range of quantities that can be measured while simultaneously reducing the cost. However, deployed sensors drift out of calibration and fail, so every sensor network requires quality control procedures to promptly detect these failures. To address these problems, we propose a two-level...
Coordinating multiple robots to achieve a complex task requires solving two distinct control problems: the high-level control problem of ensuring that each robot aims to perform a useful task (e.g., coordination) and the low-level control problem of ensuring that each robot actually performs the correct actions to achieve its task...
This dissertation explores the idea of applying machine learning technologies to help computer users find information and better organize electronic resources, by presenting the research work conducted in the following three applications: FolderPredictor, Stacking Recommendation Engines, and Integrating Learning and Reasoning.
FolderPredictor is an intelligent desktop software tool that helps...
In an increasingly computation-driven world, algorithms and mathematical models significantly impact decision making across various fields. To foster trust and understanding, it is crucial to provide users with clear and concise explanations of the reasoning behind the results produced by computational tools, especially when recommendations appear counterintuitive. Legal frameworks in...
Bayesian Optimization (BO) methods are often used to optimize an unknown function f(•) that is costly to evaluate. They typically work in an iterative manner. In each iteration, given a set of observation points, BO algorithms select k ≥ 1 points to be evaluated. The results of those points are...
In this dissertation, we present a user-in-the-loop method for the design of an interactive motion data structure that benefits from the advantages of both motion graphs and blend-based techniques. Our novel approach automatically analyzes a traditional motion graph built from labeled motion clips. The result is a more condensed, coarser...
This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...
Relational binary operators, such as join, are arguably the most costly and frequently used operations in relational data systems. In many join algorithms, the majority of the process time is spent on scanning and attempting to join the parts of the relations that do not satisfy the join condition and...
For a certain class of Z²-actions, we provide a proof of a conjecture that the ratio of the Perron eigenvalues of the transfer matrices of the free boundary restrictions converge to the entropy of that action. Also, a novel method for computing the entropy of Z²-actions is conjectured.
Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...
Correctness and efficiency are important properties of programs. However, to support maintenance and debugging, the programs should also be understandable. Program explanations also play a vital role in educational settings, enhancing the understanding of programs among students.
Proof trees provide a sound basis for generating dynamic explanations of programs. But...
There are nearly two million limb amputees living in the United States of America. Loss of limbs results in profound changes in one's life. However, the underlying neural circuitry and much of the ability to sense and control movements of their missing limb is retained even after limb loss. This...
We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
We explore the application of deep learning to the disparate fields of natural language processing and computational biology. Both the sentences uttered by humans as well as the RNA and protein sequences found within the cells of their bodies can be considered formal languages in computer science, as sets of...
Machine common sense remains a broad, potentially unbounded problem in AI. Our focus is to move toward AI systems that can develop common-sense reasoning similar to humans to detect anomalies. In particular, we study the problem of detecting the violation of expectations when object appearance or motion dynamics change from...
Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
Building intelligent computer assistants has been a long-cherished goal of AI. Many intelligent assistant systems were built and fine-tuned to specific application domains. In this work, we develop a general model of assistance that combines three powerful ideas: decision theory, hierarchical task models and probabilistic relational languages. We use the...
Many large-scale data analysis applications involve data that can vary over both time and space. Often the primary goal of analyzing spatiotemporal data is identifying trends, movements, and sudden changes with respect to time, location, or both. This can include a variety of applications in economics (housing prices, unemployment, job...
Constructing a panorama from a set of videos is a long-standing problem in computer vision. A panorama represents an enhanced still-image representation of an entire scene captured in a set of videos, where each video shows only a part of the scene. Importantly, a panorama shows only the scene background,...
Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction.
In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
This thesis studies cooperative techniques that rely on femtocell user diversity to improve the downlink communication quality of macrocell users. We analytically analyze and evaluate the achievable performance of these techniques in the downlink of Rayleigh fading channels. We provide an approximation of both the bit-error rate (BER) and the...
Software testing is a very important task during software development and it can be used to improve the quality and reliability of the software system. One potential way to reduce the cost and increase the efficiency of software testing is to generate test data automatically. Search-based approaches successfully generate unit...
Social media platforms use many techniques to engage users' attention with their platforms, including notifications, popups, and gamification elements. The impact of social media on physical and mental health has been studied, but limited publicly available research exists on how social media users can be helped to disengage from these...
Traditionally, networking protocol designs have placed much emphasis on point-to-point reliability and efficiency. With the recent rise of mobile and multimedia applications, other considerations such as power consumption and/or Quality of Service (QoS) are becoming increasingly important factors in designing network protocols. As such, we present a new flexible framework...
This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
This dissertation addresses two fundamental problems in computer vision—namely,
multitarget tracking and event recognition in videos. These problems are challenging
because uncertainty may arise from a host of sources, including motion blur,
occlusions, and dynamic cluttered backgrounds. We show that these challenges can be
successfully addressed by using a multiscale,...
This dissertation addresses a number of inter-related and fundamental problems in computer vision. Specifically, we address object discovery, recognition, segmentation, and 3D pose estimation in images, as well as 3D scene reconstruction and scene interpretation. The key ideas behind our approaches include using shape as a basic object feature, and...
The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
This dissertation addresses the problem of recognizing human activities in videos. Our focus is on activities with stochastic structure, where the activities are characterized by variable space-time arrangements of actions, and conducted by a variable number of actors. These activities occur frequently in sports and surveillance videos. They may appear...
Acting intelligently to efficiently solve sequential decision problems requires the ability to extract hierarchical structure from the underlying domain dynamics, exploit it for optimal or near-optimal decision-making, and transfer it to related problems instead of solving every problem in isolation. This dissertation makes three contributions toward this goal.
The first...
Automated recognition of object categories in images is a critical step for many real-world computer vision applications. Interest region detectors and region descriptors have been widely employed to tackle the variability of objects in pose, scale, lighting, texture, color, and so on. Different types of object recognition problems usually require...
Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
This thesis presents an interactive software tool for tracking a moving object in a video. In particular, we focus on the problem of tracking a player in American football videos. Object tracking is one of the fundamental problems in computer vision. It is one of the most important components in...
This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
The problem of document classification has been widely studied in machine learning and data mining. In document classification, most of the popular algorithms are based on the bag-of-words representation. Due to the high dimensionality of the bag-of-words representation, significant research has been conducted to reduce the dimensionality via different approaches....
Multi-relation aggregation queries process the join operator before computing the aggregation function. This join is arguably the most costly operation since traditional join algorithms spend majority of their time trying to join the parts of the relations that do not generate any output tuples. This causes slow response times with...
Counting problems are rich in opportunities for students to make meaningful mathematical connections and develop non-algorithmic thinking; their accessible nature and applications to computer science make counting problems a valuable part of mathematics curricula. However, students struggle in various ways with counting, and while previous studies have indicated that listing...