Computer Engineering Commons^™

Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu

Computer Science Faculty Publications and Presentations

Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels. Compared to regular 2D …

Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell

Computer Science Faculty Publications and Presentations

A major goal of computer vision is to enable computers to interpret visual situations—abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations— a situation model—that represent the expected spatial structure of the given situation. These …

Making Software, Making Regions: Labor Market Dualization, Segmentation, And Feminization In Austin, Portland And Seattle, Dillon Mahmoudi

Dissertations and Theses

Through mixed-methods research, this dissertation details the regionally variegated and place-specific software production processes in three second-tier US software regions. I focus on the relationship between different industrial, firm, and worker production configurations and broad-based economic development, prosperity, and inequality. I develop four main empirical findings.

First, I argue for a periodization of software production that tracks with changes in software laboring activity, software technologies, and wage-employment relationships. Through a GIS-based method, I use the IPUMS-USA to extensively measure the amount and type of software labor in industries across the US between 1970 and 2015. I map the uneven geography …

Sparse Coding On Stereo Video For Object Detection, Sheng Y. Lundquist, Melanie Mitchell, Garrett T. Kenyon

Computer Science Faculty Publications and Presentations

Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such a dataset is available. We explore the use of unsupervised sparse coding applied to stereo-video data to help alleviate the need for large amounts of labeled data. In this paper, we show that unsupervised sparse coding is able to learn disparity and motion sensitive basis functions when exposed to unlabeled stereo-video data. Additionally, we show that a DCNN that incorporates unsupervised learning exhibits better performance than fully supervised networks. Furthermore, finding a sparse representation …

Memcapacitive Devices In Logic And Crossbar Applications, Dat Tran, Christof Teuscher

Electrical and Computer Engineering Faculty Publications and Presentations

Over the last decade, memristive devices have been widely adopted in computing for various conventional and unconventional applications. While the integration density, memory property, and nonlinear characteristics have many benefits, reducing the energy consumption is limited by the resistive nature of the devices. Memcapacitors would address that limitation while still having all the benefits of memristors. Recent work has shown that with adjusted parameters during the fabrication process, a metal-oxide device can indeed exhibit a memcapacitive behavior. We introduce novel memcapacitive logic gates and memcapacitive crossbar classifiers as a proof of concept that such applications can outperform memristor-based architectures. The …

Shift-Symmetric Configurations In Two-Dimensional Cellular Automata: Irreversibility, Insolvability, And Enumeration, Peter Banda, John S. Caughman Iv, Martin Cenek, Christof Teuscher

Mathematics and Statistics Faculty Publications and Presentations

The search for symmetry as an unusual yet profoundly appealing phenomenon, and the origin of regular, repeating configuration patterns have been for a long time a central focus of complexity science, and physics.

Here, we introduce group-theoretic concepts to identify and enumerate the symmetric inputs, which result in irreversible system behaviors with undesired effects on many computational tasks. The concept of so-called configuration shift-symmetry is applied on two-dimensional cellular automata as an ideal model of computation. The results show the universal insolvability of “non-symmetric” tasks regardless of the transition function. By using a compact enumeration formula and bounding the number …

Bayesian Optimization For Refining Object Proposals, Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak

Computer Science Faculty Publications and Presentations

We develop a general-purpose algorithm using a Bayesian optimization framework for the efficient refinement of object proposals. While recent research has achieved substantial progress for object localization and related objectives in computer vision, current state-of-the-art object localization procedures are nevertheless encumbered by inefficiency and inaccuracy. We present a novel, computationally efficient method for refining inaccurate bounding-box proposals for a target object using Bayesian optimization. Offline, image features from a convolutional neural network are used to train a model to predict an object proposal’s offset distance from a target object. Online, this model is used in a Bayesian active search to …

Video Frame Interpolation Via Adaptive Convolution, Simon Niklaus, Long Mai, Feng Liu

Computer Science Faculty Publications and Presentations

Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This paper presents a robust video frame interpolation method that combines these two steps into a single process. Specifically, our method considers pixel synthesis for the interpolated frame as local convolution over two input frames. The convolution kernel captures both the local motion between the input frames and the coefficients for pixel synthesis. Our method employs a deep fully convolu- tional neural network to estimate a spatially-adaptive con- volution kernel for each pixel. This deep neural …

Cyberpdx: A Camp For Broadening Participation In Cybersecurity, Wu-Chang Feng, Robert Liebman, Lois Delcambre, Michael Mooradian Lupro, Tim Sheard, Scott Britell, Gerald W. Recktenwald

University Studies Faculty Publications and Presentations

With society’s increasing dependence on technology infrastructure, the importance of securing the computers, networks, data, and algorithms that run our digital and physical lives is becoming critical. To equip the next generation of citizens for the challenges ahead, an effort is underway to introduce security content early in a student’s academic career. It is important that these efforts broaden participation and increase diversity in the field. While many camps and curricula focus on introducing technical content and skills related to cybersecurity, such approaches can prematurely limit how students view career opportunities in the field, potentially limiting those who ultimately pursue …

Proving Non-Deterministic Computations In Agda, Sergio Antoy, Michael Hanus, Steven Libby

Computer Science Faculty Publications and Presentations

We investigate proving properties of Curry programs using Agda. First, we address the functional correctness of Curry functions that, apart from some syntactic and semantic differences, are in the intersection of the two languages. Second, we use Agda to model non-deterministic functions with two distinct and competitive approaches incorporating the non-determinism. The first approach eliminates non-determinism by considering the set of all non-deterministic values produced by an application. The second approach encodes every non-deterministic choice that the application could perform. We consider our initial experiment a success. Although proving properties of programs is a notoriously difficult task, the functional logic …