An Improved Bone Age Assessment Using Advanced Image Processing And Deep Learning Approach,
2020
Universiti Malaya
An Improved Bone Age Assessment Using Advanced Image Processing And Deep Learning Approach, Kim Meng Liang
Student Works (2020-2029)
Pediatricians often apply bone age assessment to measure the skeletal maturity of children and to predict the future height. These discrepancies are good indicators for diagnosing growth disorders. Normally, left hand skeletal is employed in this assessment. The low quality of ossification sites of carpals deteriorates the pediatrician’s visibility in inspecting the pertinent radiographic manifestations. This in turn affects the bone age assessment. Therefore, we have to enhance the quality before assessing them. Histogram equalization is one of the contrast enhancement techniques that suit this type of enhancement. Existing histogram equalizations, however, are confronting with problems in preserving the brightness …
A Process Model For Designing Performance Dashboard Using Visualization Techniques,
2020
Universiti Malaya
A Process Model For Designing Performance Dashboard Using Visualization Techniques, Bahar Muhammad Nasim
Student Works (2020-2029)
Data visualization is the presentation of data in a pictorial or graphical format. It enables decision-makers to see data analysis presented visually, so they can observe difficult concepts or identify new patterns. With interactive visualization, we can take the concept a step further by using technology to drill down into charts and graphs for more detail, interactively changing what data see and how it is processed. With the help of data visualization, it is expected to promote creative data exploration. A performance dashboard is one of the most common use cases for data visualization, and it enables decision-makers such as …
Unsupervised Monocular Depth Estimation With Multi-Scale Structural Similarity Powered Loss Function,
2020
Universiti Malaya
Unsupervised Monocular Depth Estimation With Multi-Scale Structural Similarity Powered Loss Function, Kohan Ali
Student Works (2020-2029)
Depth Estimation refers to a set of techniques and algorithms that aim to obtain a representation of spatial information of a scene. Nowadays specific hardware such as sensors, radars and multiple-view-recording cameras are being used in order to acquire depth data of a scene. Modern approaches use deep learning to address this task by trying to learn depth information in a supervised manner. However, this approach requires a large amount ground-truth data for a particular scene so that a model can be trained successfully. Also preparing ground-truth data for a range of environments is a challenging and expensive task to …
Helion’S Snapshot Module,
2020
Christopher Newport University
Helion’S Snapshot Module, Nii-Kwartei Quartey
Cybersecurity Undergraduate Research Showcase
During my undergraduate research, I spent my time working with a home automation program known as Helion, specifically, its Snapshot module. I was tasked with learning new material and completing part of the webpage that were unfinished. I also had to get a little creative when working on a design that users could find appealing. There were times I found working on Helion difficult but overall, working with Helion’s Snapshot Module is something that will help me improve with my undergraduate studies.
A Review On Eye-Tracking Metrics For Sleepiness,
2020
Singapore Management University
A Review On Eye-Tracking Metrics For Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
Sleepiness that can arise from sleep deprivation can increase human errors in task performance and create workplace hazards and accidents. Hence, it is critical to detect sleepiness to minimize hazards and human errors. This paper provides a review of the literature on eye tracking metrics that can be used to detect sleepiness. These metrics include blink duration, blink frequency, saccade latency, saccade peak velocity, saccade accuracy, smooth pursuit velocity gain, fixation rate, pupil size, and latency to pupil constriction.
Improving Event Detection Via Open-Domain Event Trigger Knowledge,
2020
Singapore Management University
Improving Event Detection Via Open-Domain Event Trigger Knowledge, Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie
Research Collection School Of Computing and Information Systems
Event Detection (ED) is a fundamental task in automatically structuring texts. Due to the small scale of training data, previous methods perform poorly on unseen/sparsely labeled trigger words and are prone to overfitting densely labeled trigger words. To address the issue, we propose a novel Enrichment Knowledge Distillation (EKD) model to leverage external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations. Experiments on benchmark ACE2005 show that our model outperforms nine strong baselines, is especially effective for unseen/sparsely labeled trigger words. The source code is released on https://github.com/shuaiwa16/ekd.git.
Hyperbolic Visual Embedding Learning For Zero-Shot Recognition,
2020
Singapore Management University
Hyperbolic Visual Embedding Learning For Zero-Shot Recognition, Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zeroshot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, i.e., learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but …
Visual Commonsense R-Cnn,
2020
Singapore Management University
Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also …
Visual Commonsense Representation Learning Via Causal Inference,
2020
Singapore Management University
Visual Commonsense Representation Learning Via Causal Inference, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the con-textual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). We extensively apply …
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection,
2020
Singapore Management University
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Research Collection School Of Computing and Information Systems
Depression is among the most prevalent mental disorders, affecting millions of people of all ages globally. Machine learning techniques have shown effective in enabling automated detection and prediction of depression for early intervention and treatment. However, they are challenged by the relative scarcity of instances of depression in the data. In this work we introduce a novel deep multi-task recurrent neural network to tackle this challenge, in which depression classification is jointly optimized with two auxiliary tasks, namely one-class metric learning and anomaly ranking. The auxiliary tasks introduce an inductive bias that improves the classification model’s generalizability on small depression …
Ntire 2020 Challenge On Video Quality Mapping: Methods And Results,
2020
Singapore Management University
Ntire 2020 Challenge On Video Quality Mapping: Methods And Results, D. Fuoli, Zhiwu Huang, M. Danelljan, R. Timofte, H. Wang, L. Jin, D. Su, J. Liu, J. Lee, M. Kudelski, L. Bala, D. Hryboy, M. Mozejko, M. Li, S. Li, B. Pang, C. Lu, Li C., He D., Li F.
Research Collection School Of Computing and Information Systems
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM), which addresses the issues of quality mapping from source video domain to target video domain. The challenge includes both a supervised track (track 1) and a weakly-supervised track (track 2) for two benchmark datasets. In particular, track 1 offers a new Internet video benchmark, requiring algorithms to learn the map from more compressed videos to less compressed videos in a supervised training manner. In track 2, algorithms are required to learn the quality mapping from one device to another when their quality varies substantially and weaklyaligned video pairs …
Design And Test Of An Autonomy Monitoring Service To Detect Divergent Behaviors On Unmanned Aerial Systems,
2020
Air Force Institute of Technology
Design And Test Of An Autonomy Monitoring Service To Detect Divergent Behaviors On Unmanned Aerial Systems, Loay Y. Almannaei
Theses and Dissertations
Operation of Unmanned Aerial Vehicles (UAV) support many critical missions in the United State Air Force (USAF). Monitoring abnormal behavior is one of many responsibilities of the operator during a mission. Some behaviors are hard to be detect by an operator, especially when flying one or more autonomous vehicles; as such, detections require a high level of attention and focus to flight parameters. In this research, a monitoring system and its algorithm are designed and tested for a target fixed-wing UAV. The Autonomy Monitoring Service (AMS) compares the real vehicle or simulated Vehicle with a similar simulated vehicle using Software …
Design Of Personalised M-Learning Curriculum Implementation Model For Diploma In Hospitality Management,
2020
Universiti Malaya
Design Of Personalised M-Learning Curriculum Implementation Model For Diploma In Hospitality Management, Ramalingam R Moganadass
Student Works (2020-2029)
Personalised m-learning allows learner to create learning experience around his mobile devices by tailoring learning materials according to his demand. This could be possible by incorporating personalised m-learning into formal education to assist students to fulfil their learning needs and learning outcomes. Therefore, this study was conducted to develop a personalised m-learning curriculum implementation model for students enrolled in Food and Beverage Service course in their diploma in hospitality programme. This study employed the Design and Development Research (DDR) approach. The Needs Analysis phases is the first phase which aimed to investigate problems and justifications for developing the personalised m-learning …
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition,
2020
Universiti Malaya
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem
Student Works (2020-2029)
Hearing and speech-impairment disability is widespread throughout the world. At present, 15 million people have this disability in the Arab world, and about 86% of them come from low- and middle-income countries. Meanwhile, sign language (SL) can be classified into standard Arabic sign language (ArSL) and local Arabic sign language (LArSL). ArSL is the formal standard and is the more acceptable SL in the Arab world; it is also considered as the medium of instructions for schools and universities as well as television news, shows and programmes. With the absence of usable ArSL recognition (ArSLR) platforms, hearing- and speech-impaired people …
Disparity-Aware Domain Adaptation In Stereo Image Restoration,
2020
Singapore Management University
Disparity-Aware Domain Adaptation In Stereo Image Restoration, Bo Yan, Chenxi Ma, Bahetiyaer Bare, Weimin Tan, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Under stereo settings, the problems of disparity estimation, stereo magnification and stereo-view synthesis have gathered wide attention. However, the limited image quality brings non-negligible difficulties in developing related applications and becomes the main bottleneck of stereo images. To the best of our knowledge, stereo image restoration is rarely studied. Towards this end, this paper analyses how to effectively explore disparity information, and proposes a unified stereo image restoration framework. The proposed framework explicitly learn the inherent pixel correspondence between stereo views and restores stereo image with the cross-view information at image and feature level. A Feature Modulation Dense Block (FMDB) …
Don't Hit Me! Glass Detection In Real-World Scenes,
2020
Singapore Management University
Don't Hit Me! Glass Detection In Real-World Scenes, Haiyang Mei, Xin Yang, Yang Wang, Yuanyuan Liu, Shengfeng He, Qiang Zhang, Xiaopeng Wei, Rynson W.H. Lau
Research Collection School Of Computing and Information Systems
Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass, and the content within the glass region is typically similar to those behind it. In this paper, we propose an important problem of detecting glass from a single RGB image. To address this problem, we construct a large-scale glass detection dataset (GDD) and design a glass detection network, called GDNet, …
Transferring And Regularizing Prediction For Semantic Segmentation,
2020
Singapore Management University
Transferring And Regularizing Prediction For Semantic Segmentation, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Dong Liu, Tao Mei
Research Collection School Of Computing and Information Systems
Semantic segmentation often requires a large set of images with pixel-level annotations. In the view of extremely expensive expert labeling, recent research has shown that the models trained on photo-realistic synthetic data (e.g., computer games) with computer-generated annotations can be adapted to real images. Despite this progress, without constraining the prediction on real images, the models will easily overfit on synthetic data due to severe domain mismatch. In this paper, we novelly exploit the intrinsic properties of semantic segmentation to alleviate such problem for model transfer. Specifically, we present a Regularizer of Prediction Transfer (RPT) that imposes the intrinsic properties …
Cookgan: Causality Based Text-To-Image Synthesis,
2020
Singapore Management University
Cookgan: Causality Based Text-To-Image Synthesis, Bin Zhu, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
This paper addresses the problem of text-to-image synthesis from a new perspective, i.e., the cause-and-effect chain in image generation. Causality is a common phenomenon in cooking. The dish appearance changes depending on the cooking actions and ingredients. The challenge of synthesis is that a generated image should depict the visual result of action-on-object. This paper presents a new network architecture, CookGAN, that mimics visual effect in causality chain, preserves fine-grained details and progressively upsamples image. Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a …
Exploring Category-Agnostic Clusters For Open-Set Domain Adaptation,
2020
Singapore Management University
Exploring Category-Agnostic Clusters For Open-Set Domain Adaptation, Yingwei Pan, Ting Yao, Yehao Li, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Unsupervised domain adaptation has received significant attention in recent years. Most of existing works tackle the closed-set scenario, assuming that the source and target domains share the exactly same categories. In practice, nevertheless, a target domain often contains samples of classes unseen in source domain (i.e., unknown class). The extension of domain adaptation from closedset to such open-set situation is not trivial since the target samples in unknown class are not expected to align with the source. In this paper, we address this problem by augmenting the state-of-the-art domain adaptation technique, Self-Ensembling, with category-agnostic clusters in target domain. Specifically, we …
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting,
2020
Tianjin University
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting, Yaoyao Liu, Yuting Su, An-An Liu, Bernt Schiele, Qianru Sun
Research Collection School Of Computing and Information Systems
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones. To alleviate this issue, it has been proposed to keep around a few examples of the previous concepts but the effectiveness of this approach heavily depends on the representativeness of these examples. This paper proposes a novel and automatic framework we call mnemonics, where we parameterize exemplars and make them optimizable in an end-to-end manner. We train the framework through bilevel optimizations, i.e., model-level and …
