Computer Sciences Commons^™

Diffuse3d: Wide-Angle 3d Photography Via Bilateral Diffusion, Yutao Jiang, Yang Zhou, Yuan Liang, Wenxi Liu, Jianbo Jiao, Yuhui Quan, Shengfeng He

Research Collection School Of Computing and Information Systems

This paper aims to resolve the challenging problem of wide-angle novel view synthesis from a single image, a.k.a. wide-angle 3D photography. Existing approaches rely on local context and treat them equally to inpaint occluded RGB and depth regions, which fail to deal with large-region occlusion (i.e., observing from an extreme angle) and foreground layers might blend into background inpainting. To address the above issues, we propose Diffuse3D which employs a pre-trained diffusion model for global synthesis, while amending the model to activate depth-aware inference. Our key insight is to alter the convolution mechanism in the denoising process. We inject depth …

Exploring Approaches To Engage K-12 Students In Learning Computational Thinking Using Collaborative Robots, Zoila Anuri Kanu

College of Engineering Summer Undergraduate Research Program

Minority students are largely underrepresented in the STEM field. The goal for this project was to develop a program which promotes the inclusion of computation skills among students and help them work collaboratively with the use of human – robot interaction. Robots are such a strong tool that can be used to enhance computational thinking and engage students towards a technical field. Through workshops and readings about computational thinking we worked on building a block-based program that introduces the uses of robots as teaching tool for computational thinking.

Rigid: Recurrent Gan Inversion And Editing Of Real Face Videos, Yangyang Xu, Shengfeng He, Kwan-Yee K. Wong, Pingluo Luo

Research Collection School Of Computing and Information Systems

GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired inconsistent results over time. In this paper, we propose a unified recurrent framework, named Recurrent vIdeo GAN Inversion and eDiting (RIGID), to explicitly and simultaneously enforce temporally coherent GAN inversion and facial editing of real videos. Our approach models the temporal relations between current and previous frames from three aspects. To enable a faithful real video reconstruction, we first maximize the inversion fidelity and consistency by learning a temporal compensated latent code. Second, we observe …

Masked Diffusion Transformer Is A Strong Image Synthesizer, Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs’ ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric masking diffusion transformer is designed to predict masked tokens from unmasked ones while maintaining the diffusion …

Ciri: Curricular Inactivation For Residue-Aware One-Shot Video Inpainting, Weiying Zheng, Cheng Xu, Xuemiao Xu, Wenxi Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking …

Supporting Artefact Awareness In Partially-Replicated Workspaces, Emran Poh, Anthony Tang, Jenanie S. Lee, Zhao Shengdong

Research Collection School Of Computing and Information Systems

Using Cross Reality (CR) approaches for remote collaboration will often result in partially-replicated workspaces. Here, workspace artefacts are not equally accessible - i.e. a physical artefact may only be manipulated by one collaborator - and in general, the artefacts become desynchronised over time. In this paper, we introduce a framework for artefact awareness that can help collaborators maintain an understanding of each others' manipulations with workspace artefacts. We illustrate our design explorations through sketches, and outline how we aim to study the effectiveness and utility of artefact awareness in cross reality remote collaboration. In our work, we expect to show …

Ubisurface: A Robotic Touch Surface For Supporting Mid-Air Planar Interactions In Room-Scale Vr, Ryota Gomi, Kazuki Takashima, Yuki Onishi, Kazuyuki Fujita, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

Room-scale VR has been considered an alternative to physical office workspaces. For office activities, users frequently require planar input methods, such as typing or handwriting, to quickly record annotations to virtual content. However, current off-The-shelf VR HMD setups rely on mid-Air interactions, which can cause arm fatigue and decrease input accuracy. To address this issue, we propose UbiSurface, a robotic touch surface that can automatically reposition itself to physically present a virtual planar input surface (VR whiteboard, VR canvas, etc.) to users and to permit them to achieve accurate and fatigue-less input while walking around a virtual room. We design …

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang

Research Collection School Of Computing and Information Systems

Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the …

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification …

Balanced Blended Space: Proposing A Universal Theoretical Framework For Combinative Reality, David Smith, Frederick Bianchi

Publications and Research

In today's fragmented societies, a unified framework for communication and collaboration across different realities is crucial. We introduce Balanced Blended Space (BBS) as a framework for describing combinative reality, encompassing virtual, physical, and conceptual realms, all intrinsically connected. Interactions within these environments shape our perceptual space. This paper outlines key axiomatic assumptions, criteria for a universal framework, and fundamental terminology. We identify deep symmetries enabling the BBS framework, including Cognitive and Computational Symmetry, Physical and Virtual Symmetry, Mediation Pathway Symmetry, Space-Time Symmetry, and Sensory Symmetry. We propose tests to determine its viability, emphasizing virtual intelligence as a collaborative partner. We …

Experiences Of Autistic Twitch Livestreamers: “I Have Made Easily The Most Meaningful And Impactful Relationships”, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg

Research Collection School Of Computing and Information Systems

We present perspectives from 10 autistic Twitch streamers regarding their experiences as livestreamers and how autism uniquely colors their experiences. Livestreaming offers a social online experience distinct from in-person, face-to-face communication, where autistic people tend to encounter challenges. Our reflexive thematic analysis of interviews with 10 participants showcases autistic livestreamers’ perspectives in their own words. Our findings center on the importance of having streamers establishing connections with other, sharing autistic identities, controlling a space for social interaction, personal growth, and accessibility challenges. In our discussion, we highlight the crucial value of having a medium for autistic representation, as well as …

Unsupervised Anomaly Detection In Medical Images With A Memory-Augmented Multi-Level Cross-Attentional Masked Autoencoder, Yu Tian, Guansong Pang, Yuyuan Liu, Chong Wang, Yuanhong Chen, Fengbei Liu, Rajvinder Singh, Johan W. Verjans, Mengyu Wang, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and Imagenet pre-trained models. Reconstruction methods, which detect anomalies from image reconstruction errors, are advantageous because they do not rely on the design of problem-specific pretext tasks needed by self-supervised approaches, and on the unreliable translation of models pre-trained from non-medical datasets. However, reconstruction methods may fail because they can have low reconstruction errors even for anomalous images. In this paper, we introduce a new reconstruction-based UAD approach …

Underwater Image Translation Via Multi-Scale Generative Adversarial Network, Dongmei Yang, Tianzi Zhang, Boquan Li, Menghao Li, Weijing Chen, Xiaoqing Li, Xingmei Wang

Research Collection School Of Computing and Information Systems

The role that underwater image translation plays assists in generating rare images for marine applications. However, such translation tasks are still challenging due to data lacking, insufficient feature extraction ability, and the loss of content details. To address these issues, we propose a novel multi-scale image translation model based on style-independent discriminators and attention modules (SID-AM-MSITM), which learns the mapping relationship between two unpaired images for translation. We introduce Convolution Block Attention Modules (CBAM) to the generators and discriminators of SID-AM-MSITM to improve its feature extraction ability. Moreover, we construct style-independent discriminators that enable the discriminant results of SID-AM-MSITM to …

Ai Vs. Ai: Can Ai Detect Ai-Generated Images?, Samah S. Baraheem, Tam Van Nguyen

Computer Science Faculty Publications

The proliferation of Artificial Intelligence (AI) models such as Generative Adversarial Net- works (GANs) has shown impressive success in image synthesis. Artificial GAN-based synthesized images have been widely spread over the Internet with the advancement in generating naturalistic and photo-realistic images. This might have the ability to improve content and media; however, it also constitutes a threat with regard to legitimacy, authenticity, and security. Moreover, implementing an automated system that is able to detect and recognize GAN-generated images is significant for image synthesis models as an evaluation tool, regardless of the input modality. To this end, we propose a framework …

Edge Distraction-Aware Salient Object Detection, Sucheng Ren, Wenxi Liu, Jianbo Jiao, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Integrating low-level edge features has been proven to be effective in preserving clear boundaries of salient objects. However, the locality of edge features makes it difficult to capture globally salient edges, leading to distraction in the final predictions. To address this problem, we propose to produce distraction-free edge features by incorporating cross-scale holistic interdependencies between high-level features. In particular, we first formulate our edge features extraction process as a boundary-filling problem. In this way, we enforce edge features to focus on closed boundaries instead of those disconnected background edges. Second, we propose to explore cross-scale holistic contextual connections between every …

Graph-Level Anomaly Detection Via Hierarchical Memory Networks, Chaoxi Niu, Guansong Pang, Ling Chen

Research Collection School Of Computing and Information Systems

Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules---node and graph memory modules---via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the …

One Font Doesn’T Fit All: The Influence Of Digital Text Personalization On Comprehension In Child And Adolescent Readers, Shannon M. Sheppard, Susanne L. Nobles, Anton Palma, Sophie Kajfez, Marjorie Jordan, Kathy Crowley, Sofie Beier

Communication Sciences and Disorders Faculty Articles and Research

Reading comprehension is an essential skill. It is unclear whether and to what degree typography and font personalization may impact reading comprehension in younger readers. With advancements in technology, it is now feasible to personalize digital reading formats in general technology tools, but this feature is not yet available for many educational tools. The current study aimed to investigate the effect of character width and inter-letter spacing on reading speed and comprehension. We enrolled 94 children (kindergarten–8th grade) and compared performance with six font variations on a word-level semantic decision task (Experiment 1) and a passage-level comprehension task (Experiment 2). …

Human Recognition Theory And Facial Recognition Technology: A Topic Modeling Approach To Understanding The Ethical Implication Of A Developing Algorithmic Technologies Landscape On How We View Ourselves And Are Viewed By Others, Hajer Albalawi

Electronic Theses and Dissertations, 2020-2023

The emergence of algorithmic-driven technology has significantly impacted human life in the current century. Algorithms, as versatile constructs, hold different meanings across various disciplines, including computer science, mathematics, social science, and human-artificial intelligence studies. This study defines algorithms from an ethical perspective as the foundation of an information society and focuses on their implications in the context of human recognition. Facial recognition technology, driven by algorithms, has gained widespread use, raising important ethical questions regarding privacy, bias, and accuracy. This dissertation aims to explore the impact of algorithms on machine perception of human individuals and how humans perceive one another …

Studying Memes During Covid Lockdown As A Lens Through Which To Understand Video-Mediated Communication Interactions, Tatyana Claytor

Electronic Theses and Dissertations, 2020-2023

The purpose of this study is to analyze image macros about video-mediated communication (VMC) created during the time frame of 2020-2021 when people all over the world started using Zoom and VMC for work and school. It is a unique opportunity to study how users' interactions with themselves and with others were affected at a time when a lot of people started using the technology at the same time. Because the focus is on interactions, I narrowed it down to three topics to analyze the memes: presence, self, and space and place to analyze the memes. I chose memes relating …

Visual And Spatial Audio Mismatching In Virtual Environments, Zachary Lawrence Garris

Theses and Dissertations

This paper explores how vision affects spatial audio perception in virtual reality. We created four virtual environments with different reverb and room sizes, and recorded binaural clicks in each one. We conducted two experiments: one where participants judged the audio-visual match, and another where they pointed to the click direction. We found that vision influences spatial audio perception and that congruent audio-visual cues improve accuracy. We suggest some implications for virtual reality design and evaluation.

Signings Of Graphs And Sign-Symmetric Signed Graphs, Ahmad Asiri

Theses and Dissertations

In this dissertation, we investigate various aspects of signed graphs, with a particular focus on signings and sign-symmetric signed graphs. We begin by examining the complete graph on six vertices with one edge deleted ($K_6$\textbackslash e) and explore the different ways of signing this graph up to switching isomorphism. We determine the frustration index (number) of these signings and investigate the existence of sign-symmetric signed graphs. We then extend our study to the $K_6$\textbackslash 2e graph and the McGee graph with exactly two negative edges. We investigate the distinct ways of signing these graphs up to switching isomorphism and demonstrate …

Understanding The Role Of Interactivity And Explanation In Adaptive Experiences, Lijie Guo

All Dissertations

Adaptive experiences have been an active area of research in the past few decades, accompanied by advances in technology such as machine learning and artificial intelligence. Whether the currently ongoing research on adaptive experiences has focused on personalization algorithms, explainability, user engagement, or privacy and security, there is growing interest and resources in developing and improving these research focuses. Even though the research on adaptive experiences has been dynamic and rapidly evolving, achieving a high level of user engagement in adaptive experiences remains a challenge. %????? This dissertation aims to uncover ways to engage users in adaptive experiences by incorporating …

All Hands On Deck: Choosing Virtual End Effector Representations To Improve Near Field Object Manipulation Interactions In Extended Reality, Roshan Venkatakrishnan

All Dissertations

Extended reality, or "XR", is the adopted umbrella term that is heavily gaining traction to collectively describe Virtual reality (VR), Augmented reality (AR), and Mixed reality (MR) technologies. Together, these technologies extend the reality that we experience either by creating a fully immersive experience like in VR or by blending in the virtual and "real" worlds like in AR and MR.

The sustained success of XR in the workplace largely hinges on its ability to facilitate efficient user interactions. Similar to interacting with objects in the real world, users in XR typically interact with virtual integrants like objects, menus, windows, …

Anatoview: Using Interactive 3d Visualizations With Augmented Reality Support For Laypersons’ Medical Education In Informed Consent Processes, Michelle Chen

Dartmouth College Master’s Theses

AnatoView is an interactive multimedia educational application that visualizes medical procedures in three-dimensional (3D), augmented reality (AR) space. By providing visual and spatial information of medical procedures, AnatoView acts as a learning supplement for laypersons/patients in informed consent (IC) processes — wherein instructional content is traditionally limited to purely spoken explanations that lead to poor patient comprehension. We design a mixed study and conduct a randomized, controlled trial with 15 laypersons as participants: administering a traditional IC process to a control group, and an IC process supplemented by the use of AnatoView to experimental groups. As a primary outcome, medical …

The Effects Of Primary And Secondary Task Workloads On Cybersickness In Immersive Virtual Active Exploration Experiences, Rohith Venkatakrishnan

All Dissertations

Virtual reality (VR) technology promises to transform humanity. The technology enables users to explore and interact with computer-generated environments that can be simulated to approximate or deviate from reality. This creates an endless number of ways to propitiously apply the technology in our lives. It follows that large technological conglomerates are pushing for the widespread adoption of VR, financing the creation of the Metaverse - a hypothetical representation of the next iteration of the internet.

Even with VR technology's continuous growth, its widespread adoption remains long overdue. This can largely be attributed to an affliction called cybersickness, an analog to …

Flood: A Flexible Invariant Learning Framework For Out-Of-Distribution Generalization On Graphs, Yang Liu, Xiang Ao, Fuli Feng, Yunshan Ma, Kuan Li, Tat‑Seng Chua, Qing He

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) have achieved remarkable success in various domains but most of them are developed under the in-distribution assumption. Under out-of-distribution (OOD) settings, they suffer from the distribution shift between the training set and the test set and may not generalize well to the test distribution. Several methods have tried the invariance principle to improve the generalization of GNNs in OOD settings. However, in previous solutions, the graph encoder is immutable after the invariant learning and cannot be adapted to the target distribution flexibly. Confronting the distribution shift, a flexible encoder with refinement to the target distribution can …

Hyperbolic Graph Topic Modeling Network With Continuously Updated Topic Tree, Ce Zhang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Connectivity across documents often exhibits a hierarchical network structure. Hyperbolic Graph Neural Networks (HGNNs) have shown promise in preserving network hierarchy. However, they do not model the notion of topics, thus document representations lack semantic interpretability. On the other hand, a corpus of documents usually has high variability in degrees of topic specificity. For example, some documents contain general content (e.g., sports), while others focus on specific themes (e.g., basketball and swimming). Topic models indeed model latent topics for semantic interpretability, but most assume a flat topic structure and ignore such semantic hierarchy. Given these two challenges, we propose a …

Socialz: Multi-Feature Social Fuzz Testing, Francisco Zanartu, Christoph Treude, Markus Wagner

Research Collection School Of Computing and Information Systems

Online social networks have become an integral aspect of our daily lives and play a crucial role in shaping our relationships with others. However, bugs and glitches, even minor ones, can cause anything from frustrating problems to serious data leaks that can have farreaching impacts on millions of users. To mitigate these risks, fuzz testing, a method of testing with randomised inputs, can provide increased confidence in the correct functioning of a social network. However, implementing traditional fuzz testing methods can be prohibitively difficult or impractical for programmers outside of the network’s development team. To tackle this challenge, we present …

Balanced Blended Space: Foundational Human–Ai Dialogues In A Symmetry-Based Mediation Framework, David Smith

Publications and Research

This working paper documents the early development of the Balanced Blended Space (BBS) framework through a series of iterative interactions between a cognitive agent (human researcher) and a computational agent (AI system) conducted in 2023. The work is motivated by the need for a universal theoretical model capable of describing the integration of physical, virtual, and conceptual spaces, particularly in response to increasing fragmentation across contemporary communication systems.

BBS is proposed as a symmetry-based mediation framework in which relationships between domains—such as physical and virtual space, cognition and computation, and multiple sensory modalities—are treated as structurally equivalent and mappable. Central …

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a …