Understanding The Dynamic Visual World: From Motion To Semantics, 2020 University of Massachusetts Amherst
Understanding The Dynamic Visual World: From Motion To Semantics, Huaizu Jiang
Doctoral Dissertations
We live in a dynamic world, which is continuously in motion. Perceiving and interpreting the dynamic surroundings is an essential capability for an intelligent agent. Human beings have the remarkable capability to learn from limited data, with partial or little annotation, in sharp contrast to computational perception models that rely on large-scale, manually labeled data. Reliance on strongly supervised models with manually labeled data inherently prohibits us from modeling the dynamic visual world, as manual annotations are tedious, expensive, and not scalable, especially if we would like to solve multiple scene understanding tasks at the same time. Even worse, in …
Responsive Web Design, 2020 CUNY New York City College of Technology
Responsive Web Design, Ashley Varon, David Karlins
Publications and Research
Responsive web design is one of the most important topics in web. It can be one of the main reasons a website can be costing a business clients, and creating an effect on a business. The rise in popularity of mobile phones and tablets makes it crucial for a website to be designed to respond and adjust to different viewports. This project will research how important responsive web design is in 2020 and the positive or negative impacts it may have on the users, customers, and businesses. Companies must consider text size, layout, navigation, image sizes, and testing when designing …
A Study Of Multi-Task And Region-Wise Deep Learning For Food Ingredient Recognition, 2020 Fudan University
A Study Of Multi-Task And Region-Wise Deep Learning For Food Ingredient Recognition, Jingjing Chen, Bin Zhu, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Food recognition has captured numerous research attention for its importance for health-related applications. The existing approaches mostly focus on the categorization of food according to dish names, while ignoring the underlying ingredient composition. In reality, two dishes with the same name do not necessarily share the exact list of ingredients. Therefore, the dishes under the same food category are not mandatorily equal in nutrition content. Nevertheless, due to limited datasets available with ingredient labels, the problem of ingredient recognition is often overlooked. Furthermore, as the number of ingredients is expected to be much less than the number of food categories, …
Argumentation Stance Polarity And Intensity Prediction And Its Application For Argumentation Polarization Modeling And Diverse Social Connection Recommendation, 2020 University of Arkansas, Fayetteville
Argumentation Stance Polarity And Intensity Prediction And Its Application For Argumentation Polarization Modeling And Diverse Social Connection Recommendation, Joseph Winstead Sirrianni
Graduate Theses and Dissertations
Cyber argumentation platforms implement theoretical argumentation structures that promote higher quality argumentation and allow for informative analysis of the discussions. Dr. Liu’s research group has designed and implemented a unique platform called the Intelligent Cyber Argumentation System (ICAS). ICAS structures its discussions into a weighted cyber argumentation graph, which describes the relationships between the different users, their posts in a discussion, the discussion topic, and the various subtopics in a discussion. This platform is unique as it encodes online discussions into weighted cyber argumentation graphs based on the user’s stances toward one another’s arguments and ideas. The resulting weighted cyber …
Envrment: Investigating Experience In A Virtual User-Composed Environment, 2020 California Polytechnic State University, San Luis Obispo
Envrment: Investigating Experience In A Virtual User-Composed Environment, Matthew Key
Master's Theses
Virtual Reality is a technology that has long held society's interest, but has only recently began to reach a critical mass of everyday consumers. The idea of modern VR can be traced back decades, but because of the limitations of the technology (both hardware and software), we are only now exploring its potential. At present, VR can be used for tele-surgery, PTSD therapy, social training, professional meetings, conferences, and much more. It is no longer just an expensive gimmick to go on a momentary field trip; it is a tool, and as with the automobile, personal computer, and smartphone, it …
Sharper Generalisation Bounds For Pairwise Learning, 2020 Singapore Management University
Sharper Generalisation Bounds For Pairwise Learning, Yunwen Lei, Antoine Ledent, Marius Kloft
Research Collection School Of Computing and Information Systems
Pairwise learning refers to learning tasks with loss functions depending on a pair of training examples, which includes ranking and metric learning as specific examples. Recently, there has been an increasing amount of attention on the generalization analysis of pairwise learning to understand its practical behavior. However, the existing stability analysis provides suboptimal high-probability generalization bounds. In this paper, we provide a refined stability analysis by developing generalization bounds which can be √nn-times faster than the existing results, where nn is the sample size. This implies excess risk bounds of the order O(n−1/2) (up to a logarithmic factor) for both …
Making Sense Of Online Public Health Debates With Visual Analytics Systems, 2020 The University of Western Ontario
Making Sense Of Online Public Health Debates With Visual Analytics Systems, Anton Ninkov
Electronic Thesis and Dissertation Repository
Online debates occur frequently and on a wide variety of topics. Particularly, online debates about various public health topics (e.g., vaccines, statins, cannabis, dieting plans) are prevalent in today’s society. These debates are important because of the real-world implications they can have on public health. Therefore, it is important for public health stakeholders (i.e., those with a vested interest in public health) and the general public to have the ability to make sense of these debates quickly and effectively. This dissertation investigates ways of enabling sense-making of these debates with the use of visual analytics systems (VASes). VASes are computational …
Global Context Aware Convolutions For 3d Point Cloud Understanding, 2020 Singapore Management University
Global Context Aware Convolutions For 3d Point Cloud Understanding, Zhiyuan Zhang, Binh-Son Hua, Wei Chen, Yibin Tian, Sai-Kit Yeung
Research Collection School Of Computing and Information Systems
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. …
Exploring And Evaluating Attributes, Values, And Structures For Entity Alignment, 2020 Singapore Management University
Exploring And Evaluating Attributes, Values, And Structures For Entity Alignment, Zhiyuan Liu, Yixin Cao, Liangming Pan, Juanzi Li, Zhiyuan Liu, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performance by modeling the KG structure defined by relation triples. However, attribute triples can also provide crucial alignment signal but have not been well explored yet. In this paper, we propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently. Besides, the performances of current EA methods are overestimated because of the name-bias of existing EA datasets. To make an objective …
Tangi: Tangible Proxies For Embodied Object Exploration And Manipulation In Virtual Reality, 2020 Singapore Management University
Tangi: Tangible Proxies For Embodied Object Exploration And Manipulation In Virtual Reality, Martin Feick, Scott Bateman, Anthony Tang, Anthony Tang
Research Collection School Of Computing and Information Systems
Exploring and manipulating complex virtual objects is challenging due to limitations of conventional controllers and free-hand interaction techniques. We present the TanGi toolkit which enables novices to rapidly build physical proxy objects using Composable Shape Primitives. TanGi also provides Manipulators allowing users to build objects including movable parts, making them suitable for rich object exploration and manipulation in VR. With a set of different use cases and applications we show the capabilities of the TanGi toolkit and evaluate its use. In a study with 16 participants, we demonstrate that novices can quickly build physical proxy objects using the Composable Shape …
Cost-Sensitive Deep Forest For Price Prediction, 2020 Singapore Management University
Cost-Sensitive Deep Forest For Price Prediction, Chao Ma, Zhenbing Liu, Zhiguang Cao, Wen Song, Jie Zhang, Weiliang Zeng
Research Collection School Of Computing and Information Systems
For many real-world applications, predicting a price range is more practical and desirable than predicting a concrete value. In this case, price prediction can be regarded as a classification problem. Although deep forest is recognized as the best solution to many classification problems, a crucial issue limits its direct application to price prediction, i.e., it treated all the misclassifications equally no matter how far away they are from the real classes, since their impacts on the accuracy are the same. This is unreasonable to price prediction as the misclassification should be as close to the real price range as possible …
Espade: An Efficient And Semantically Secure Shortest Path Discovery For Outsourced Location-Based Services, 2020 Montclair State University
Espade: An Efficient And Semantically Secure Shortest Path Discovery For Outsourced Location-Based Services, Bharath K. Samanthula, Divyadharshini Karthikeyan, Boxiang Dong, K. Anitha Kumari
Department of Computer Science Faculty Scholarship and Creative Works
With the rapid growth of smart devices and technological advancements in tracking geospatial data, the demand for Location-Based Services (LBS) is facing a constant rise in several domains, including military, healthcare and transportation. It is a natural step to migrate LBS to a cloud environment to achieve on-demand scalability and increased resiliency. Nonetheless, outsourcing sensitive location data to a third-party cloud provider raises a host of privacy concerns as the data owners have reduced visibility and control over the outsourced data. In this paper, we consider outsourced LBS where users want to retrieve map directions without disclosing their location information. …
Cross-Domain Cross-Modal Food Transfer, 2020 Singapore Management University
Cross-Domain Cross-Modal Food Transfer, Bin Zhu, Chong-Wah Ngo, Jingjing Chen
Research Collection School Of Computing and Information Systems
The recent works in cross-modal image-to-recipe retrieval pave a new way to scale up food recognition. By learning the joint space between food images and recipes, food recognition is boiled down as a retrieval problem by evaluating the similarity of embedded features. The major drawback, nevertheless, is the difficulty in applying an already-trained model to recognize different cuisines of dishes unknown to the model. In general, model updating with new training examples, in the form of image-recipe pairs, is required to adapt a model to new cooking styles in a cuisine. Nevertheless, in practice, acquiring sufficient number of image-recipe pairs …
Activity River: Visualizing Planned And Logged Personal Activities For Reflection, 2020 Singapore Management University
Activity River: Visualizing Planned And Logged Personal Activities For Reflection, Bon Adriel Aseniero, Charles Perin, Wesley Willett, Anthony Tang, Sheelagh Carpendale
Research Collection School Of Computing and Information Systems
We present Activity River, a personal visualization tool which enables individuals to plan, log, and reflect on their self-defined activities. We are interested in supporting this type of reflective practice as prior work has shown that reflection can help people plan and manage their time effectively. Hence, we designed Activity River based on five design goals (visualize historical and contextual data, facilitate comparison of goals and achievements, engage viewers with delightful visuals, support authorship, and enable flexible planning and logging) which we distilled from the Information Visualization and Human-Computer Interaction literature. To explore our approach's strengths and limitations, we conducted …
Zoomwalls: Dynamic Walls That Simulate Haptic Infrastructure For Room-Scale Vr World, 2020 Singapore Management University
Zoomwalls: Dynamic Walls That Simulate Haptic Infrastructure For Room-Scale Vr World, Yan Yixian, Kazuki Takashima, Anthony Tang, Takayuki Tanno, Kazuyuki Fujita, Yoshifumi Kitamura
Research Collection School Of Computing and Information Systems
We focus on the problem of simulating the haptic infrastructure of a virtual environment (i.e. walls, doors). Our approach relies on multiple ZoomWalls---autonomous robotic encounter-type haptic wall-shaped props---that coordinate to provide haptic feedback for room-scale virtual reality. Based on a user's movement through the physical space, ZoomWall props are coordinated through a predict-and-dispatch architecture to provide just-in-time haptic feedback for objects the user is about to touch. To refine our system, we conducted simulation studies of different prediction algorithms, which helped us to refine our algorithmic approach to realize the physical ZoomWall prototype. Finally, we evaluated our system through a …
Multi-Modal Cooking Workflow Construction For Food Recipes, 2020 Singapore Management University
Multi-Modal Cooking Workflow Construction For Food Recipes, Liangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Yugang Jiang, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Understanding food recipe requires anticipating the implicit causal effects of cooking actions, such that the recipe can be converted into a graph describing the temporal workflow of the recipe. This is a non-trivial task that involves common-sense reasoning. However, existing efforts rely on hand-crafted features to extract the workflow graph from recipes due to the lack of large-scale labeled datasets. Moreover, they fail to utilize the cooking images, which constitute an important part of food recipes. In this paper, we build MM-ReS, the first large-scale dataset for cooking workflow construction, consisting of 9,850 recipes with human-labeled workflow graphs. Cooking steps …
Interpretable Embedding For Ad-Hoc Video Search, 2020 Singapore Management University
Interpretable Embedding For Ad-Hoc Video Search, Jiaxin Wu, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Answering query with semantic concepts has long been the mainstream approach for video search. Until recently, its performance is surpassed by concept-free approach, which embeds queries in a joint space as videos. Nevertheless, the embedded features as well as search results are not interpretable, hindering subsequent steps in video browsing and query reformulation. This paper integrates feature embedding and concept interpretation into a neural network for unified dual-task learning. In this way, an embedding is associated with a list of semantic concepts as an interpretation of video content. This paper empirically demonstrates that, by using either the embedding features or …
Gesture Enhanced Comprehension Of Ambiguous Human-To-Robot Instructions, 2020 Singapore Management University
Gesture Enhanced Comprehension Of Ambiguous Human-To-Robot Instructions, Weerakoon Mudiyanselage Dulanga Kaveesha Weerakoon, Vigneshwaran Subbaraju, Nipuni Karumpulli, Minh Anh Tuan Tran, Qianli Xu, U-Xuan Tan, Joo Hwee Lim, Archan Misra
Research Collection School Of Computing and Information Systems
This work demonstrates the feasibility and benefits of using pointing gestures, a naturally-generated additional input modality, to improve the multi-modal comprehension accuracy of human instructions to robotic agents for collaborative tasks.We present M2Gestic, a system that combines neural-based text parsing with a novel knowledge-graph traversal mechanism, over a multi-modal input of vision, natural language text and pointing. Via multiple studies related to a benchmark table top manipulation task, we show that (a) M2Gestic can achieve close-to-human performance in reasoning over unambiguous verbal instructions, and (b) incorporating pointing input (even with its inherent location uncertainty) in M2Gestic results in a significant …
Deeprhythm: Exposing Deepfakes With Attentional Visual Heartbeat Rhythms, 2020 Singapore Management University
Deeprhythm: Exposing Deepfakes With Attentional Visual Heartbeat Rhythms, Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, Jianjun Zhao
Research Collection School Of Computing and Information Systems
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors. Motivated by the fact that remote visual photoplethysmography (PPG) is made possible by monitoring the minuscule periodic changes of skin color due to blood pumping through the face, we conjecture that normal heartbeat rhythms found in the real face videos will be disrupted or even entirely broken in a DeepFake video, making it a potentially powerful indicator for DeepFake detection. In this work, we propose DeepRhythm, a DeepFake …
Knowledge Enhanced Neural Fashion Trend Forecasting, 2020 Singapore Management University
Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Furthermore, to effectively model the time series data of fashion elements with rather complex patterns, we propose …