Graphics and Human Computer Interfaces Commons^™

State Graph Reasoning For Multimodal Conversational Recommendation, Yuxia Wu, Lizi Liao, Gangyi Zhang, Wenqiang Lei, Guoshuai Zhao, Xueming Qian, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational recommendation system (CRS) attracts increasing attention in various application domains such as retail and travel. It offers an effective way to capture users’ dynamic preferences with multi-turn conversations. However, most current studies center on the recommendation aspect while over-simplifying the conversation process. The negligence of complexity in data structure and conversation flow hinders their practicality and utility. In reality, there exist various relationships among slots and values, while users’ requirements may dynamically adjust or change. Moreover, the conversation often involves visual modality to facilitate the conversation. These actually call for a more advanced internal state representation of the dialogue …

Deconfounded Visual Grounding, Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial languagelocation association without visual reasoning, e.g., grounding any language query containing sheep to the nearly central regions, due to that most queries about sheep have groundtruth locations at the image center. First, we frame the visual grounding pipeline into a causal graph, which shows the causalities among image, query, target location and underlying confounder. Through the causal graph, we know how to break the …

Modeling Functional Similarity In Source Code With Graph-Based Siamese Networks, Nikita Mehrotra, Navdha Agarwal, Piyush Gupta, Saket Anand, David Lo, Rahul Purandare

Research Collection School Of Computing and Information Systems

Code clones are duplicate code fragments that share (nearly) similar syntax or semantics. Code clone detection plays an important role in software maintenance, code refactoring, and reuse. A substantial amount of research has been conducted in the past to detect clones. A majority of these approaches use lexical and syntactic information to detect clones. However, only a few of them target semantic clones. Recently, motivated by the success of deep learning models in other fields, including natural language processing and computer vision, researchers have attempted to adopt deep learning techniques to detect code clones. These approaches use lexical information (tokens) …

Modeling Sentiments And Preferences From Multimodal Data, Quoc Tuan Truong

Dissertations and Theses Collection (Open Access)

Online reviews are prevalent in many modern Web applications, such as e-commerce, crowd-sourced location and check-in platforms. Fueled by the rise of mobile phones that are often the only cameras on hand, reviews are increasingly multimodal, with photos in addition to textual content. In this thesis, we focus on modeling the subjectivity carried in this form of data, with two research objectives.

In the first part, we tackle the problem of detecting sentiment expressed by a review. This is a key unlocking many applications, e.g., analyzing opinions, monitoring consumer satisfaction, assessing product quality.
Traditionally, the task of sentiment analysis primarily …

Deep Graph-Level Anomaly Detection By Glocal Knowledge Distillation, Rongrong Ma, Guansong Pang, Ling Chen, Anton Van Den Hengel

Research Collection School Of Computing and Information Systems

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal in their fine-grained (node-level) or holistic (graph-level) properties, respectively. To tackle this challenge we introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations. The random distillation is achieved by …

Cross-Modal Food Retrieval: Learning A Joint Embedding Of Food Images And Recipes With Semantic Consistency And Attention Mechanism, Hao Wang, Doyen Sahoo, Chenghao Liu, Ke Shu, Palakorn Achananuparp, Ee-Peng Lim, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food data; and 2) difficulties in obtaining discriminative recipe representations. To address these …

Toward Video-Conferencing Tools For Hands-On Activities In Online Teaching, Audrey Labrie, Terrance Mok, Anthony Tang, Michelle Lui, Lora Oehlberg, Lev Poretski

Research Collection School Of Computing and Information Systems

Many instructors in computing and HCI disciplines use hands-on activities for teaching and training new skills. Beyond simply teaching hands-on skills like sketching and programming, instructors also use these activities so students can acquire tacit skills. Yet, current video-conferencing technologies may not effectively support hands-on activities in online teaching contexts. To develop an understanding of the inadequacies of current video-conferencing technologies for hands-on activities, we conducted 15 interviews with university-level instructors who had quickly pivoted their use of hands-on activities to an online context during the early part of the COVID-19 pandemic. Based on our analysis, we uncovered four pedagogical …

Kg4vis: A Knowledge Graph-Based Approach For Visualization Recommendation, Haotian Li, Yong Wang, Songheng Zhang, Yangqiu Song, Huamin. Qu

Research Collection School Of Computing and Information Systems

Visualization recommendation or automatic visualization generation can significantly lower the barriers for general users to rapidly create effective data visualizations, especially for those users without a background in data visualizations. However, existing rule-based approaches require tedious manual specifications of visualization rules by visualization experts. Other machine learning-based approaches often work like black-box and are difficult to understand why a specific visualization is recommended, limiting the wider adoption of these approaches. This paper fills the gap by presenting KG4Vis, a knowledge graph (KG)-based approach for visualization recommendation. It does not require manual specifications of visualization rules and can also guarantee good …

Deep Learning For Video-Grounded Dialogue Systems, Hung Le

Dissertations and Theses Collection (Open Access)

In recent years, we have witnessed significant progress in building systems with artificial intelligence. However, despite advancements in machine learning and deep learning, we are still far from achieving autonomous agents that can perceive multi-dimensional information from the surrounding world and converse with humans in natural language. Towards this goal, this thesis is dedicated to building intelligent systems in the task of video-grounded dialogues. Specifically, in a video-grounded dialogue, a system is required to hold a multi-turn conversation with humans about the content of a video. Given an input video, a dialogue history, and a question about the video, the …

Self-Supervised Learning Disentangled Group Representation As Feature, Tan Wang, Zhongqi Yue, Jianqiang Huang, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this paper, we formulate the notion of “good” representation from a group-theoretic view using Higgins’ definition of disentangled representation [38], and show that existing Self-Supervised Learning (SSL) only disentangles simple augmentation features such as rotation and colorization, thus unable to modularize the remaining semantics. To break the limitation, we propose an iterative SSL algorithm: Iterative Partition-based Invariant Risk Minimization (IP-IRM), which successfully grounds the abstract semantics and the group acting on them into concrete contrastive learning. …

Vireo @ Trecvid 2021 Ad-Hoc Video Search, Jiaxin Wu, Phuong Anh Nguyen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

In this paper, we summarize our submitted runs and results for Ad-hoc Video Search (AVS) task at TRECVid 2020

A Theory-Driven Self-Labeling Refinement Method For Contrastive Representation Learning, Pan Zhou, Caiming Xiong, Xiao-Tong Yuan

Research Collection School Of Computing and Information Systems

For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination, while accurate labels benefit its generalization. Inspired by this theory, we propose a novel …

Fine-Grained Generalization Analysis Of Inductive Matrix Completion, Antoine Ledent, Rodrigo Alves, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

In this paper, we bridge the gap between the state-of-the-art theoretical results for matrix completion with the nuclear norm and their equivalent in \textit{inductive matrix completion}: (1) In the distribution-free setting, we prove bounds improving the previously best scaling of \widetilde{O}(rd2) to \widetilde{O}(d3/2√r), where d is the dimension of the side information and rr is the rank. (2) We introduce the (smoothed) \textit{adjusted trace-norm minimization} strategy, an inductive analogue of the weighted trace norm, for which we show guarantees of the order \widetilde{O}(dr) under arbitrary sampling. In the inductive case, a similar rate was previously achieved only under uniform sampling …

Towards Balancing Vr Immersion And Bystander Awareness, Yoshiki Kudo, Anthony Tang, Kazuyuki Fujita, Isamu Endo, Kazuki Takashima, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

Head-mounted displays (HMDs) increase immersion into virtual worlds. The problem is that this limits headset users' awareness of bystanders: headset users cannot attend to bystanders' presence and activities. We call this the HMD boundary. We explore how to make the HMD boundary permeable by comparing different ways of providing informal awareness cues to the headset user about bystanders. We adapted and implemented three visualization techniques (Avatar View, Radar and Presence++) that share bystanders' location and orientation with headset users. We conducted a hybrid user and simulation study with three different types of VR content (high, medium, low interactivity) with twenty …

Intercept Graph: An Interactive Radial Visualization For Comparison Of State Changes, Shaolun Ruan, Yong Wang, Qiang Guan

Research Collection School Of Computing and Information Systems

State change comparison of multiple data items is often necessary in multiple application domains, such as medical science, financial engineering, sociology, biological science, etc. Slope graphs and grouped bar charts have been widely used to show a “before-and-after” story of different data states and indicate their changes. However, they visualize state changes as either slope or difference of bars, which has been proved less effective for quantitative comparison. Also, both visual designs suffer from visual clutter issues with an increasing number of data items. In this paper, we propose Intercept Graph, a novel visual design to facilitate effective interactive comparison …

Self-Supervised Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) that requires only normal (healthy) training images is an important tool for enabling the development of medical image analysis (MIA) applications, such as disease screening, since it is often difficult to collect and annotate abnormal (or disease) images in MIA. However, heavily relying on the normal images may cause the model training to overfit the normal class. Self-supervised pre-training is an effective solution to this problem. Unfortunately, current self-supervision methods adapted from computer vision are sub-optimal for MIA applications because they do not explore MIA domain knowledge for designing the pretext tasks or the training process. …

Exploiting Reasoning Chains For Multi-Hop Science Question Answering, Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam

Research Collection School Of Computing and Information Systems

We propose a novel Chain Guided Retriever reader (CGR) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing explainable reasoning without the need of any corpus-specific annotations, such as the ground-truth reasoning chain, or human annotated entity mentions. Specifically, we first generate reasoning chains from a semantic graph constructed by Abstract Meaning Representation of retrieved evidence facts. A Chain-aware loss, concerning both local and global chain information, is also designed to enable the generated chains to serve as distant supervision signals for training the retriever, where reinforcement learning is also adopted to …

Wav-Bert: Cooperative Acoustic And Linguistic Representation Learning For Low-Resource Speech Recognition, Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin

Research Collection School Of Computing and Information Systems

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic …

Learning To Teach And Learn For Semi-Supervised Few-Shot Image Classification, Xinzhe Li, Jianqiang Huang, Yaoyao Liu, Qin Zhou, Shibao Zheng, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

This paper presents a novel semi-supervised few-shot image classification method named Learning to Teach and Learn (LTTL) to effectively leverage unlabeled samples in small-data regimes. Our method is based on self-training, which assigns pseudo labels to unlabeled data. However, the conventional pseudo-labeling operation heavily relies on the initial model trained by using a handful of labeled data and may produce many noisy labeled samples. We propose to solve the problem with three steps: firstly, cherry-picking searches valuable samples from pseudo-labeled data by using a soft weighting network; and then, cross-teaching allows the classifiers to teach mutually for rejecting more noisy …

Transporting Causal Mechanisms For Unsupervised Domain Adaptation, Zhongqi Yue, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the feature will inevitably lose nondiscriminative semantics in source domain, which is however discriminative in target domain. We use a causal view—transportability theory [41]—to identify that such loss is in fact a confounding effect, which can only be removed by causal intervention. However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the …

A Large-Scale Benchmark For Food Image Segmentation, Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun

Research Collection School Of Computing and Information Systems

Food image segmentation is a critical and indispensible task for developing health-related applications such as estimating food calories and nutrients. Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks—the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e.g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different …

Prediction Of Synthetic Lethal Interactions In Human Cancers Using Multi-View Graph Auto-Encoder, Zhifeng Hao, Di Wu, Yuan Fang, Min Wu, Ruichu Cai, Xiaoli Li

Research Collection School Of Computing and Information Systems

Synthetic lethality (SL) is a very important concept for the development of targeted anticancer drugs. However, experimental methods for SL detection often suffer from various issues like high cost and low consistency across cell lines. Hence, computational methods for predicting novel SLs have recently emerged as complements for wet-lab experiments. In addition, SL data can be represented as a graph where nodes are genes and edges are the SL interactions. It is thus motivated to design advanced graph-based machine learning algorithms for SL prediction. In this paper, we propose a novel SL prediction method using Multi-view Graph Auto-Encoder (SLMGAE). We …

Condensing A Sequence To One Informative Frame For Video Recognition, Qiu. Zhaofan, Ting Yao, Yan Shu, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Video is complex due to large variations in motion and rich content in fine-grained visual details. Abstracting useful information from such information-intensive media requires exhaustive computing resources. This paper studies a two-step alternative that first condenses the video sequence to an informative" frame" and then exploits off-the-shelf image recognition system on the synthetic frame. A valid question is how to define" useful information" and then distill it from a video sequence down to one synthetic frame. This paper presents a novel Informative Frame Synthesis (IFS) architecture that incorporates three objective tasks, ie, appearance reconstruction, video categorization, motion estimation, and two …

Causal Attention For Unbiased Visual Recognition, Tan Wang, Chang Zhou, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Attention module does not always help deep models learn causal features that are robust in any confounding context, e.g., a foreground object feature is invariant to different backgrounds. This is because the confounders trick the attention to capture spurious correlations that benefit the prediction when the training and testing data are IID (identical & independent distribution); while harm the prediction when the data are OOD (out-of-distribution). The sole fundamental solution to learn causal attention is by causal intervention, which requires additional annotations of the confounders, e.g., a “dog” model is learned within “grass+dog” and “road+dog” respectively, so the “grass” and …

The Efficacy Of Collaborative Authoring Of Video Scene Descriptions, Rosiana Natalie, Jolene Kar Inn Loh, Huei Suen Tan, Joshua Shi-Hao Tseng, Ian Luke Yi-Ren Chan, Ebrima H. Jarjue, Hernisa Kacorri, Kotaro Hara

Research Collection School Of Computing and Information Systems

The majority of online video contents remain inaccessible to people with visual impairments due to the lack of audio descriptions to depict the video scenes. Content creators have traditionally relied on professionals to author audio descriptions, but their service is costly and not readily-available. We investigate the feasibility of creating more cost-effective audio descriptions that are also of high quality by involving novices. Specifically, we designed, developed, and evaluated ViScene, a web-based collaborative audio description authoring tool that enables a sighted novice author and a reviewer either sighted or blind to interact and contribute to scene descriptions (SDs)—text that can …

Visionary Caption: Improving The Accessibility Of Presentation Slides Through Highlighting Visualization, Carmen Ji Yan Yip, Jie Mi Chong, Sin Yee Kwek, Yong Wang, Kotaro Hara

Research Collection School Of Computing and Information Systems

Presentation slides are widely used in occasions such as academic talks and business meetings. Captions placed on slides support deaf and hard of hearing (DHH) people to understand spoken contents, but simultaneously comprehending and associating visual contents on slides and caption text could be challenging. In this paper, we design and develop a visualization technique to highlight and associate chart on a slide and numerical data in caption. We first conduct a small formative study with people with and without hearing impairments to assess the value of the visualization technique using a lo-fidelity video prototype. We then develop Visionary Caption, …

Conquer: Contextual Query-Aware Ranking For Video Corpus Moment Retrieval, Zhijian Hou, Chong-Wah Ngo, W. K. Chan

Research Collection School Of Computing and Information Systems

This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel CONtextual QUery-awarE Ranking (CONQUER) model for effective moment localization and ranking. CONQUER explores query context for multi-modal fusion and representation learning in two different steps. The first step derives fusion weights for the adaptive combination of multi-modal video content. The second step performs bi-directional attention to tightly couple video and query as a single joint representation for moment localization. As query context is …

Uncovering Patterns In Reviewers' Feedback To Scene Description Authors, Rosiana Natalie, Jolene Kar Inn Loh, Huei Suen Tan, Joshua Shi-Hao Tseng, Hernisa Kacorri, Kotaro Hara

Research Collection School Of Computing and Information Systems

Audio descriptions (ADs) can increase access to videos for blind people. Researchers have explored different mechanisms for generating ADs, with some of the most recent studies involving paid novices; to improve the quality of their ADs, novices receive feedback from reviewers. However, reviewer feedback is not instantaneous. To explore the potential for real-time feedback through automation, in this paper, we analyze 1,120 comments that 40 sighted novices received from a sighted or a blind reviewer. We find that feedback patterns tend to fall under four themes: (i) Quality; commenting on different AD quality variables, (ii) Speech Act; the utterance or …

Route Tapestries: Navigating 360° Virtual Tour Videos Using Slit-Scan Visualizations, Jiannan Li, Jiahe Lyu, Maurício Sousa, Ravin Balakrishnan, Anthony Tang, Tovi Grossman

Research Collection School Of Computing and Information Systems

An increasingly popular way of experiencing remote places is by viewing 360° virtual tour videos, which show the surrounding view while traveling through an environment. However, finding particular locations in these videos can be difficult because current interfaces rely on distorted frame previews for navigation. To alleviate this usability issue, we propose Route Tapestries, continuous orthographic-perspective projection of scenes along camera routes. We first introduce an algorithm for automatically constructing Route Tapestries from a 360° video, inspired by the slit-scan photography technique. We then present a desktop video player interface using a Route Tapestry timeline for navigation. An online evaluation …

Holoboard: A Large-Format Immersive Teaching Board Based On Pseudo Holographics, Jiangtao Gong, Teng Han, Siling Guo, Jiannan Li, Siyu Zha, Liuxin Zhang, Feng Tian, Qianying Wang, Yong Rui

Research Collection School Of Computing and Information Systems

In this paper, we present HoloBoard, an interactive large-format pseduo-holographic display system for lecture based classes. With its unique properties of immersive visual display and transparent screen, we designed and implemented a rich set of novel interaction techniques like immersive presentation, role-play, and lecturing behind the scene that are potentially valuable for lecturing in class. We conducted a controlled experimental study to compare a HoloBoard class with a normal class through measuring students’ learning outcomes and three dimensions of engagement (i.e., behavioral, emotional, and cognitive engagement). We used pre-/post- knowledge tests and multimodal learning analytics to measure students’ learning outcomes …