Computer Sciences Commons^™

Learning Interpretable Concept Groups In Cnns, Saurabh Varshneya, Antoine Ledent, Rob Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft

Research Collection School Of Computing and Information Systems

We propose a novel training methodology---Concept Group Learning (CGL)---that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL's model interpretability using standard interpretability evaluation …

An Empirical Study Of The Discreteness Prior In Low-Rank Matrix Completion, Rodrigo Alves, Antoine Ledent, Renato Assunção, Marius And Kloft

Research Collection School Of Computing and Information Systems

A reasonable assumption in recommender systems is that the rows (users) and columns (items) of the rating matrix can be split into groups (communities) with the following property: each entry of the matrix is the sum of components corresponding to community behavior and a purely low-rank component corresponding to individual behavior. We investigate (1) whether such a structure is present in real-world datasets, (2) whether the knowledge of the existence of such structure alone can improve performance, without explicit information about the community memberships. To these ends, we formulate a joint optimization problem over all (completed matrix, set of communities) …

A Survey On Ml4vis: Applying Machine Learning Advances To Data Visualization, Qianwen Wang, Zhutian Chen, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VIS is needed. In this article, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: “what visualization processes can be assisted by ML?” and “how ML techniques can be used to solve visualization problems? ” This survey reveals seven main processes where …

Invertible Grayscale With Sparsity Enforcing Priors, Yong Du, Yangyang Xu, Taizhong Ye, Qiang Wen, Chufeng Xiao, Junyu Dong, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Color dimensionality reduction is believed as a non-invertible process, as re-colorization results in perceptually noticeable and unrecoverable distortion. In this article, we propose to convert a color image into a grayscale image that can fully recover its original colors, and more importantly, the encoded information is discriminative and sparse, which saves storage capacity. Particularly, we design an invertible deep neural network for color encoding and decoding purposes. This network learns to generate a residual image that encodes color information, and it is then combined with a base grayscale image for color recovering. In this way, the non-differentiable compression process (e.g., …

Are Missing Links Predictable? An Inferential Benchmark For Knowledge Graph Completion, Yixin Cao, Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen, Hanwang Zhang

Research Collection School Of Computing and Information Systems

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns. First, each testing sample is predictable with supportive data in the training set. To ensure it, we propose to utilize rule-guided train/test generation, instead of conventional random split. Second, InferWiki initiates the evaluation following the open-world assumption and improves the inferential difficulty of the closed-world assumption, by providing manually annotated negative and unknown triples. Third, we include various inference patterns (e.g., reasoning path length and types) for comprehensive evaluation. In experiments, we curate two settings of InferWiki varying in sizes …

Bidding Mechanisms In Graph Games, Guy Avni, Thomas A. Henzinger, Dorde Zikelic

Research Collection School Of Computing and Information Systems

A graph game proceeds as follows: two players move a token through a graph to produce a finite or infinite path, which determines the payoff of the game. We study bidding games in which in each turn, an auction determines which player moves the token. Bidding games were largely studied in combination with two variants of first-price auctions called “Richman” and “poorman” bidding. We study taxman bidding, which span the spectrum between the two. The game is parameterized by a constant τ∈[0,1]: portion τ of the winning bid is paid to the other player, and portion 1−τ to the bank. …

Collaborative Development Of Spatial Audio Virtual Environments, George V. Landon, Austin K. Jaquith

Frameless

Access to the newest features of Virtual Reality headsets has become increasingly more accessible to student developers in recent years. Manufacturers are competing to support all available device features not just through their Software Development Kits (SDKs), but also integrated into industry-standard game engines. One particular feature, spatial sound, can now be deployed without directly accessing the SDK but instead modifying deployment settings and selecting checkboxes. This accessibility to new VR developers has opened up new opportunities for inter-disciplinary collaborations within constrained development cycles like an academic semester.

Rotateentry: Controller-Rolling-Style Text Entry For Three Degrees Of Freedom Virtual Reality Devices, Ziming Li, Roshan Peiris

Frameless

In this work, we propose RotateEntry, a controller-rolling-style method for text entry on three degrees of freedom virtual reality devices. To move the key-selecting cursor in two dimensions on a QWERTY layout virtual keyboard, we developed three variants of RotateEntry: Rotate Column Rotate, Rotate Key, and Rotate Column Point. We conducted a comparative empirical evaluation of the four text input methods, including three proposed controller-rolling-style text input methods and the standard raycasting-style one. Text entry performance, accuracy, workload, usability, and user experience were tested and evaluated. Due to the COVID-19 situation, our study was conducted remotely. The impact of using …

Vr Cinema, Simarjot Khanna

Frameless

A virtual reality cinema experience using a decent smartphone and Google Cardboard or similar inexpensive VR Headsets.

Computational Frameworks For Multi-Robot Cooperative 3d Printing And Planning, Laxmi Prasad Poudel

Graduate Theses and Dissertations

This dissertation proposes a novel cooperative 3D printing (C3DP) approach for multi-robot additive manufacturing (AM) and presents scheduling and planning strategies that enable multi-robot cooperation in the manufacturing environment. C3DP is the first step towards achieving the overarching goal of swarm manufacturing (SM). SM is a paradigm for distributed manufacturing that envisions networks of micro-factories, each of which employs thousands of mobile robots that can manufacture different products on demand. SM breaks down the complicated supply chain used to deliver a product from a large production facility from one part of the world to another. Instead, it establishes a network …

The Design Of A Framework For The Detection Of Web-Based Dark Patterns, Andrea Curley, Dympna O'Sullivan, Damian Gordon, Brendan Tierney, Ioannis Stavrakakis

Conference Papers

In the theories of User Interfaces (UI) and User Experience (UX), the goal is generally to help understand the needs of users and how software can be best configured to optimize how the users can interact with it by removing any unnecessary barriers. However, some systems are designed to make people unwillingly agree to share more data than they intend to, or to spend more money than they plan to, using deception or other psychological nudges. User Interface experts have categorized a number of these tricks that are commonly used and have called them Dark Patterns. Dark Patterns are varied …

Towards A Large-Scale Intelligent Mobile-Argumentation And Discovering Arguments, Controversial Topics And Topic-Oriented Focal Sets In Cyber-Argumentation, Najla Althuniyan

Graduate Theses and Dissertations

User-generated content (UGC) platforms host different forms of information, such as audio, video, pictures, and text. They have many online applications, such as social media, blogs, photo and video sharing, customer reviews, debate, and deliberation platforms. Usually, the content of these platforms is provided and consumed by users. Most of these platforms, mainly social media and blogs, are often used for online discussion. These platforms offer tools for users to share and express opinions. Commonly, people from different backgrounds and origins discuss opinions about various issues over the Internet. Furthermore, discussions among users contain substantial information from which knowledge about …

Design And Development Of Techniques To Ensure Integrity In Fog Computing Based Databases, Abdulwahab Fahad S. Alazeb

Graduate Theses and Dissertations

The advancement of information technology in coming years will bring significant changes to the way sensitive data is processed. But the volume of generated data is rapidly growing worldwide. Technologies such as cloud computing, fog computing, and the Internet of things (IoT) will offer business service providers and consumers opportunities to obtain effective and efficient services as well as enhance their experiences and services; increased availability and higher-quality services via real-time data processing augment the potential for technology to add value to everyday experiences. This improves human life quality and easiness. As promising as these technological innovations, they are prone …

How Important Is The Train-Validation Split In Meta-Learning?, Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, D. Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong

Research Collection School Of Computing and Information Systems

Meta-learning aims to perform fast adaptation on a new task through learning a “prior” from multiple existing tasks. A common practice in meta-learning is to perform a train-validation split (train-val method) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split. Despite its prevalence, the importance of the train-validation split is not well understood either in theory or in practice, particularly in comparison to the more direct train-train method, which uses all the pertask data for both training and evaluation. We provide a detailed theoretical study on whether …

Unified Conversational Recommendation Policy Learning Via Graph-Based Reinforcement Learning, Yang Deng, Yaliang Li, Fei Sun, Bolin Ding, Wai Lam

Research Collection School Of Computing and Information Systems

Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attributes to ask, which items to recommend, and when to ask or recommend, at each conversation turn. However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure. In the light of these challenges, we propose …

Emotioncues: Emotion-Oriented Visual Summarization Of Classroom Videos, Haipeng Zeng, Xinhuan Shu, Yanbang Wang, Yong Wang, Liguo Zhang, Ting-Chuen Pong, Huamin Qu

Research Collection School Of Computing and Information Systems

Analyzing students' emotions from classroom videos can help both teachers and parents quickly know the engagement of students in class. The availability of high-definition cameras creates opportunities to record class scenes. However, watching videos is time-consuming, and it is challenging to gain a quick overview of the emotion distribution and find abnormal emotions. In this paper, we propose EmotionCues, a visual analytics system to easily analyze classroom videos from the perspective of emotion summary and detailed analysis, which integrates emotion recognition algorithms with visualizations. It consists of three coordinated views: a summary view depicting the overall emotions and their dynamic …

Automated Privacy Protection For Mobile Device Users And Bystanders In Public Spaces, David Darling

Graduate Theses and Dissertations

As smartphones have gained popularity over recent years, they have provided usersconvenient access to services and integrated sensors that were previously only available through larger, stationary computing devices. This trend of ubiquitous, mobile devices provides unparalleled convenience and productivity for users who wish to perform everyday actions such as taking photos, participating in social media, reading emails, or checking online banking transactions. However, the increasing use of mobile devices in public spaces by users has negative implications for their own privacy and, in some cases, that of bystanders around them.

Specifically, digital photography trends in public have negative implications for …

Dehumor: Visual Analytics For Decomposing Humor, Xingbo Wang, Yao Ming, Tongshuang Wu, Haipeng Zeng, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Despite being a critical communication skill, grasping humor is challenginga successful use of humor requires a mixture of both engaging content build-up and an appropriate vocal delivery (e.g., pause). Prior studies on computational humor emphasize the textual and audio features immediately next to the punchline, yet overlooking longer-term context setup. Moreover, the theories are usually too abstract for understanding each concrete humor snippet. To fill in the gap, we develop DeHumor, a visual analytical system for analyzing humorous behaviors in public speaking. To intuitively reveal the building blocks of each concrete example, DeHumor decomposes each humorous video into multimodal features …

Line Sampling In Participating Media, Hsu Cheng

Dartmouth College Master’s Theses

Participating media, such as fog, fire, dust, and smoke, surrounds us in our daily life. Rendering participating media efficiently has always been a challenging task in physically based rendering. Line sampling has been derived to be an alternative method in direct lighting recently. Since line sampling takes visibility into account, it could reduce variance in the same render time compared to point sampling. We leverage the benefits of line sampling in the context of evaluating direct lighting in participating media. We express the direct lighting as a three-dimensional integral and perform line sampling in any one of them. We show …

Pandemic Pivot: Designing A Participatory Simulation To Support Social Distancing And Remote Learning, K. K. Lamberty, Paul Friederichsen, Audrey Le Meur, Joseph Moonan Walbran

Computer Science Publications

Participatory simulations usually aim to bring simulations off screen into a shared physical space with people acting as agents in the simulation. In this paper, we describe considerations and design decisions related to creating a participatory simulation for use in learning settings with restrictions imposed due to the COVID-19 pandemic where typical classroom interactions were no longer allowed. We describe how our design decisions might help children both “dive in” and “step out” to understand more about pollinators and the prairie in spite of various restrictions on how exactly they can interact with each other. Our simulation, Buzz About, uses …

Exploring The Relationship Between Intrinsic Motivation And Receptivity To Mhealth Interventions, Sarah Hong

Dartmouth College Undergraduate Theses

Recent research in mHealth has shown the promise of Just-in-Time Adaptive Interventions (JITAIs). JITAIs aim to deliver the right type and amount of support at the right time. Choosing the right delivery time involves determining a user's state of receptivity, that is, the degree to which a user is willing to accept, process, and use the intervention provided.

Although past work on generic phone notifications has found evidence that users are more likely to respond to notifications with content they view as useful, there is no existing research on whether users' intrinsic motivation for the underlying topic of mHealth …

Exploring Material Representations For Sparse Voxel Dags, Steven Pineda

Master's Theses

Ray tracing is a popular technique used in movies and video games to create compelling visuals. Ray traced computer images are increasingly becoming more realistic and almost indistinguishable from real-word images. Due to the complexity of scenes and the desire for high resolution images, ray tracing can become very expensive in terms of computation and memory. To address these concerns, researchers have examined data structures to efficiently store geometric and material information. Sparse voxel octrees (SVOs) and directed acyclic graphs (DAGs) have proven to be successful geometric data structures for reducing memory requirements. Moxel DAGs connect material properties to these …

Assessing Real-Time Flow Experience In Human-Computer Interaction: An Electroencephalogram (Eeg) Study, Fiona Fui-Hoon Nah, Tejaswini Yelamanchili, Keng Siau, Langtao Chen

Research Collection School Of Computing and Information Systems

An optimal experience termed flow can be experienced by users who are deeply involved in human-computer interaction (HCI). The electroencephalogram (EEG) provides an innovative way to assess in real-time if users are approaching or experiencing the flow state in various applications of HCI. However, the current literature remains unclear and inconsistent with regard to the relationship between EEG activity and flow experience. The objective of this research is to assess EEG activity corresponding to the state of flow. A laboratory experiment was conducted to collect EEG data of the flow and other states (including baseline) in the context of HCI.

Real-Time Stylized Rendering For Large-Scale 3d Scenes, Jack Pietrok

Master's Theses

While modern digital entertainment has seen a major shift toward photorealism in animation, there is still significant demand for stylized rendering tools. Stylized, or non-photorealistic rendering (NPR), applications generally sacrifice physical accuracy for artistic or functional visual output. Oftentimes, NPR applications focus on extracting specific features from a 3D environment and highlighting them in a unique manner. One application of interest involves recreating 2D hand-drawn art styles in a 3D-modeled environment. This task poses challenges in the form of spatial coherence, feature extraction, and stroke line rendering. Previous research on this topic has also struggled to overcome specific performance bottlenecks, …

Learning Contextual Causality Between Daily Events From Time-Consecutive Images, Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth

Research Collection School Of Computing and Information Systems

Conventional textual-based causal knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often limited. Moreover, as no context is provided during the annotation, the resulting causal knowledge records (e.g., ConceptNet) typically do not consider the context. In this paper, we move out of the textual domain to explore a more scalable way of acquiring causal knowledge and investigate the possibility of learning contextual causality from the visual signal. Specifically, we first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that with good language and visual representations, it is possible to …

Generating Face Images With Attributes For Free, Yaoyao Liu, Qianru Sun, He Xiangnan, Liu An-An, Su Yuting, Chua Tat-Seng

Research Collection School Of Computing and Information Systems

With superhuman-level performance of face recognition, we are more concerned about the recognition of fine-grained attributes, such as emotion, age, and gender. However, given that the label space is extremely large and follows a long-tail distribution, it is quite expensive to collect sufficient samples for fine-grained attributes. This results in imbalanced training samples and inferior attribute recognition models. To this end, we propose the use of arbitrary attribute combinations, without human effort, to synthesize face images. In particular, to bridge the semantic gap between high-level attribute label space and low-level face image, we propose a novel neural-network-based approach that maps …

Engaging Drivers Via Competition: A Case Study With Arena, Hao Cheng, Shuyu Wei, Lingyu Zhang, Zimu Zhou, Yongxin. Tong

Research Collection School Of Computing and Information Systems

Sustained work enthusiasms of drivers are crucial for the success of large-scale ride-hailing platforms. In this paper, we conduct the first-of-its-kind exploration to encourage active participation of drivers via competition. We design Arena, a competition where drivers compete for prizes via completing more trips. Through a pilot study covering over 2,600 participants, we uncover the easy-win problem, an overlooked and serious issue in competition design for real-world drivers. It refers to situations where one competitor does not show up during competition whereas the other easily wins. To solve the easy-win problem without impairing motivation of drivers, we devise a novel …

Cache-Efficient Fork-Processing Patterns On Large Graphs, Shengliang Lu, Shixuan Sun, Johns Paul, Yuchen Li, Bingsheng He

Research Collection School Of Computing and Information Systems

As large graph processing emerges, we observe a costly fork-processing pattern (FPP) that is common in many graph algorithms. The unique feature of the FPP is that it launches many independent queries from different source vertices on the same graph. For example, an algorithm in analyzing the network community profile can execute Personalized PageRanks that start from tens of thousands of source vertices at the same time. We study the efficiency of handling FPPs in state-of-the-art graph processing systems on multi-core architectures, including Ligra, Gemini, and GraphIt. We find that those systems suffer from severe cache miss penalty because of …

Projecting Your View Attentively: Monocular Road Scene Layout Estimation Via Cross-View Transformation, Weixiang Yang, Qi Li, Wenxi Liu, Yuanlong Yu, Yuexin Ma, Shengfeng He, Jia Pan

Research Collection School Of Computing and Information Systems

HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to the deployed expensive sensors and time-consuming computation. Camera-based methods usually need to separately perform road segmentation and view transformation, which often causes distortion and the absence of content. To push the limits of the technology, we present a novel framework that enables reconstructing a local map formed by road layout and vehicle occupancy in the bird's-eye view given a front-view monocular image only. In particular, we propose a cross-view transformation module, which takes the constraint of cycle consistency between views into account and makes full use …

Reciprocal Transformations For Unsupervised Video Object Segmentation, Sucheng Ren, Wenxi Liu, Yongtuo Liu, Haoxin Chen, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Unsupervised video object segmentation (UVOS) aims at segmenting the primary objects in videos without any human intervention. Due to the lack of prior knowledge about the primary objects, identifying them from videos is the major challenge of UVOS. Previous methods often regard the moving objects as primary ones and rely on optical flow to capture the motion cues in videos, but the flow information alone is insufficient to distinguish the primary objects from the background objects that move together. This is because, when the noisy motion features are combined with the appearance features, the localization of the primary objects is …