Visual Commonsense Representation Learning Via Causal Inference,
2020
Singapore Management University
Visual Commonsense Representation Learning Via Causal Inference, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the con-textual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). We extensively apply …
Don't Hit Me! Glass Detection In Real-World Scenes,
2020
Singapore Management University
Don't Hit Me! Glass Detection In Real-World Scenes, Haiyang Mei, Xin Yang, Yang Wang, Yuanyuan Liu, Shengfeng He, Qiang Zhang, Xiaopeng Wei, Rynson W.H. Lau
Research Collection School Of Computing and Information Systems
Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass, and the content within the glass region is typically similar to those behind it. In this paper, we propose an important problem of detecting glass from a single RGB image. To address this problem, we construct a large-scale glass detection dataset (GDD) and design a glass detection network, called GDNet, …
Design Of Personalised M-Learning Curriculum Implementation Model For Diploma In Hospitality Management,
2020
Universiti Malaya
Design Of Personalised M-Learning Curriculum Implementation Model For Diploma In Hospitality Management, Ramalingam R Moganadass
Student Works (2020-2029)
Personalised m-learning allows learner to create learning experience around his mobile devices by tailoring learning materials according to his demand. This could be possible by incorporating personalised m-learning into formal education to assist students to fulfil their learning needs and learning outcomes. Therefore, this study was conducted to develop a personalised m-learning curriculum implementation model for students enrolled in Food and Beverage Service course in their diploma in hospitality programme. This study employed the Design and Development Research (DDR) approach. The Needs Analysis phases is the first phase which aimed to investigate problems and justifications for developing the personalised m-learning …
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition,
2020
Universiti Malaya
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem
Student Works (2020-2029)
Hearing and speech-impairment disability is widespread throughout the world. At present, 15 million people have this disability in the Arab world, and about 86% of them come from low- and middle-income countries. Meanwhile, sign language (SL) can be classified into standard Arabic sign language (ArSL) and local Arabic sign language (LArSL). ArSL is the formal standard and is the more acceptable SL in the Arab world; it is also considered as the medium of instructions for schools and universities as well as television news, shows and programmes. With the absence of usable ArSL recognition (ArSLR) platforms, hearing- and speech-impaired people …
Disparity-Aware Domain Adaptation In Stereo Image Restoration,
2020
Singapore Management University
Disparity-Aware Domain Adaptation In Stereo Image Restoration, Bo Yan, Chenxi Ma, Bahetiyaer Bare, Weimin Tan, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Under stereo settings, the problems of disparity estimation, stereo magnification and stereo-view synthesis have gathered wide attention. However, the limited image quality brings non-negligible difficulties in developing related applications and becomes the main bottleneck of stereo images. To the best of our knowledge, stereo image restoration is rarely studied. Towards this end, this paper analyses how to effectively explore disparity information, and proposes a unified stereo image restoration framework. The proposed framework explicitly learn the inherent pixel correspondence between stereo views and restores stereo image with the cross-view information at image and feature level. A Feature Modulation Dense Block (FMDB) …
Video Synthesis From The Stylegan Latent Space,
2020
San Jose State University
Video Synthesis From The Stylegan Latent Space, Lei Zhang
Master's Projects
Generative models have shown impressive results in generating synthetic images. However, video synthesis is still difficult to achieve, even for these generative models. The best videos that generative models can currently create are a few seconds long, distorted, and low resolution. For this project, I propose and implement a model to synthesize videos at 1024x1024x32 resolution that include human facial expressions by using static images generated from a Generative Adversarial Network trained on the human facial images. To the best of my knowledge, this is the first work that generates realistic videos that are larger than 256x256 resolution from single …
Graphical Representation Of Text Semantics,
2020
Kennesaw State University
Graphical Representation Of Text Semantics, Karl Kevin Tiba Fossoh
Master of Science in Computer Science Theses
A text is a set of words conveying a particular semantic based on their order, representation and structure. Those elements can be associated through a different set of interpretations, based on frequency and proportionality. The problem with context is that numbers do not help understand the semantics and fall short to convey the message of the text. The graphical representation of text semantics focuses on the conversion of text to images. Contrarily to word clouds that simply produce frequency mapping of words within the text and topic models that essentially give context to word frequencies and proportionalities, images keep intact …
Exploring Attacks And Defenses In Additive Manufacturing Processes: Implications In Cyber-Physical Security,
2020
Washington University in St. Louis
Exploring Attacks And Defenses In Additive Manufacturing Processes: Implications In Cyber-Physical Security, Nicholas Deily
McKelvey School of Engineering Graduate Student Theses & Dissertations
Many industries are rapidly adopting additive manufacturing (AM) because of the added versatility this technology offers over traditional manufacturing techniques. But with AM, there comes a unique set of security challenges that must be addressed. In particular, the issue of part verification is critically important given the growing reliance of safety-critical systems on 3D printed parts. In this thesis, the current state of part verification technologies will be examined in the con- text of AM-specific geometric-modification attacks, and an automated tool for 3D printed part verification will be presented. This work will cover: 1) the impacts of malicious attacks on …
Exploring Usage Of Web Resources Through A Model Of Api Learning,
2020
Washington University in St. Louis
Exploring Usage Of Web Resources Through A Model Of Api Learning, Finn Voichick
McKelvey School of Engineering Graduate Student Theses & Dissertations
Application programming interfaces (APIs) are essential to modern software development, and new APIs are frequently being produced. Consequently, software developers must regularly learn new APIs, which they typically do on the job from online resources rather than in a formal educational context. The Kelleher–Ichinco COIL model, an acronym for “Collection and Organization of Information for Learning,” was recently developed to model the entire API learning process, drawing from information foraging theory, cognitive load theory, and external memory research. We ran an exploratory empirical user study in which participants performed a programming task using the React API with the goal of …
Voxel Optimization,
2020
Minnesota State University Moorhead
Voxel Optimization, Scott Bengs
Student Academic Conference
Voxel Optimization This poster presentation covers optimization for voxels. They can be thought of as three dimensional pixels. Vo coming from volume and xel from pixel. Voxels are just values placed in a 3D grid. Voxels have many interesting uses in the medical and scientific field, especially in geology. One use in computer science is storing world information for video games or graphical applications. One very popular example is Minecraft, a game that allows all of the world to be changed, that uses cube shaped voxels. The first topic will be on the naive approach of building a model from …
Server Score,
2020
Minnesota State University Moorhead
Server Score, Zachary Buresh
Student Academic Conference
This presentation is in regards to the Android mobile application that I developed in the Kotlin programming language named "Server Score". The app helps waiters/waitresses calculate, track, and predict performance related statistics on the job.
User Experience As A Rhetorical Medium: User At The Intersection Of Audience, Reader And Actor,
2020
College of the Holy Cross
User Experience As A Rhetorical Medium: User At The Intersection Of Audience, Reader And Actor, Áine Doyle
English Honors Theses
The goal of this project is to demonstrate how digital interfaces are bodies of visual language that can be “close-read” and interpreted critically, just like any other traditional text; digital user interfaces, like poetry and novels, have form and content that complement and shape the meaning and interpretation of the other. It is meant to encourage academic discussions about digital interfaces to go beyond whether social media is “good” or “bad” to how digital interfaces are structured, why they are structured the way they are, and what effects these structures have on the way they communicate information and content to …
Generating Acoustic Projections Using 3d Models,
2020
James Madison University
Generating Acoustic Projections Using 3d Models, Jake A. Brazelton
Senior Honors Projects, 2020-current
Raytracing is used in commercial graphics engines most commonly for lighting effects, but it also has many uses when it comes to acoustic simulation. Adopted directly from these computer graphics programs, the formulas presented herein enable the visualization of acoustic intensity levels throughout a 3D space using Python 3 and the OpenGL library. In addition to visualization, they also provide the ability to calculate the reverberation time and critical distance of an enclosed space in relation to its size and material makeup. The described application bundles all of these components together in a Qt5 application that allows users to view …
Investigating Machine Learning Techniques For Gesture Recognition With Low-Cost Capacitive Sensing Arrays,
2020
University of Arkansas, Fayetteville
Investigating Machine Learning Techniques For Gesture Recognition With Low-Cost Capacitive Sensing Arrays, Michael Fahr Jr.
Computer Science and Computer Engineering Undergraduate Honors Theses
Machine learning has proven to be an effective tool for forming models to make predictions based on sample data. Supervised learning, a subset of machine learning, can be used to map input data to output labels based on pre-existing paired data. Datasets for machine learning can be created from many different sources and vary in complexity, with popular datasets including the MNIST handwritten dataset and CIFAR10 image dataset. The focus of this thesis is to test and validate multiple machine learning models for accurately classifying gestures performed on a low-cost capacitive sensing array. Multiple neural networks are trained using gesture …
Speech Processing In Computer Vision Applications,
2020
University of Arkansas, Fayetteville
Speech Processing In Computer Vision Applications, Nicholas Waterworth
Computer Science and Computer Engineering Undergraduate Honors Theses
Deep learning has been recently proven to be a viable asset in determining features in the field of Speech Analysis. Deep learning methods like Convolutional Neural Networks facilitate the expansion of specific feature information in waveforms, allowing networks to create more feature dense representations of data. Our work attempts to address the problem of re-creating a face given a speaker's voice and speaker identification using deep learning methods. In this work, we first review the fundamental background in speech processing and its related applications. Then we introduce novel deep learning-based methods to speech feature analysis. Finally, we will present our …
Connecting The Dots For People With Autism: A Data-Driven Approach To Designing And Evaluating A Global Filter,
2020
Chapman University
Connecting The Dots For People With Autism: A Data-Driven Approach To Designing And Evaluating A Global Filter, Viseth Sean
Computational and Data Sciences (PhD) Dissertations
"Social communication is the use of language in social contexts. It encompasses social interaction, social cognition, pragmatics, and language processing” [3]. One presumed prerequisite of social communication is visual attention–the focus of this work. “Visual attention is a process that directs a tiny fraction of the information arriving at primary visual cortex to high-level centers involved in visual working memory and pattern recognition” [7]. This process involves the integration of two streams: the global and local streams; the global stream rapidly processes the scene, and the local stream processes details. This integration is important to social communication in that attending …
Assistance For Target Selection In Mobile Augmented Reality,
2020
Singapore Management University
Assistance For Target Selection In Mobile Augmented Reality, Vinod Asokan, Scott Bateman, Anthony Tang
Research Collection School Of Computing and Information Systems
Mobile augmented reality - where a mobile device is used to view and interact with virtual objects displayed in the real world - is becoming more common. Target selection is the main method of interaction in mobile AR, but is particularly difficult because targets in AR can have challenging characteristics such as being moving or occluded (by digital or real world objects). Because target selection is particularly difficult and error prone in mobile AR, we conduct a comparative study of target assistance techniques. We compared four different cursor-based selection techniques against the standard touch-to-select interaction, finding that a newly adapted …
Starhopper: A Touch Interface For Remote Object-Centric Drone Navigation,
2020
Singapore Management University
Starhopper: A Touch Interface For Remote Object-Centric Drone Navigation, Jiannan Li, Ravin Balakrishnan, Tovi Grossman
Research Collection School Of Computing and Information Systems
Camera drones, a rapidly emerging technology, offer people the ability to remotely inspect an environment with a high degree of mobility and agility. However, manual remote piloting of a drone is prone to errors. In contrast, autopilot systems can require a significant degree of environmental knowledge and are not necessarily designed to support flexible visual inspections. Inspired by camera manipulation techniques in interactive graphics, we designed StarHopper, a novel touch screen interface for efficient object-centric camera drone navigation, in which a user directly specifies the navigation of a drone camera relative to a specified object of interest. The system relies …
Tidytouch: An Interactive Visualization Tool For Data Science Education,
2020
East Tennessee State University
Tidytouch: An Interactive Visualization Tool For Data Science Education, Jonah E. Devaney
Undergraduate Honors Theses
Accessibility and usability of software define the programs used for both professional and academic activities. While many proprietary tools are easy to grasp, some challenges exist in using more technical resources, such as the statistical programming language R. The creative project tidyTouch is a web application designed to help educate any user in basic R data visualization and transformation using the popular ggplot2 and dplyr packages. Providing point-and-click interactivity to explore potential modifications of graphics for data presentation, the application uses an intuitive interface to make R more accessible to those without programming experience. This project is in a state …
Use Of Eye-Tracking To Identify Psychological Indicators Of Sleepiness,
2020
Singapore Management University
Use Of Eye-Tracking To Identify Psychological Indicators Of Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah, Matthew Thimgan
Research Collection School Of Computing and Information Systems
Sleepiness or sleep deprivation creates a serious hazard or obstacle to task execution and performance. Sleep deprivation can be life-threating (e.g., when driving or executing attention-critical tasks). We are interested to examine if eye-tracking technology can be used to assess and detect sleepiness in an online environment. In this research proposal, we will focus on examining the relationships between sleepiness and parameters involving pupil size, blinks, and saccades.
