Open Access. Powered by Scholars. Published by Universities.®

Graphics and Human Computer Interfaces Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year

Articles 511 - 540 of 936

Full-Text Articles in Graphics and Human Computer Interfaces

Tenet: Triple Excitation Network For Video Salient Object Detection, Sucheng Ren, Chu Han, Xin Yang, Guoqiang Han, Shengfeng He Aug 2020

Tenet: Triple Excitation Network For Video Salient Object Detection, Sucheng Ren, Chu Han, Xin Yang, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations. These excitation mechanisms are designed following the spirit of curriculum learning and aim to reduce learning ambiguities at the beginning of training by selectively exciting feature activations using ground truth. Then we gradually reduce the weight of ground truth excitations by a curriculum rate and replace it by a curriculum complementary map for better and faster convergence. In particular, the spatial excitation strengthens feature activations for clear object …

Go to article

Interface Design Of Web-Based Educational Platforms For Young Students, Lurong He, Fiona Fui-Hoon Nah Aug 2020

Interface Design Of Web-Based Educational Platforms For Young Students, Lurong He, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

With the outbreak of the Covid-19 pandemic, almost all the school programs in the United States are closed. Most educational programs have moved online. Both teachers and students are facing challenges adapting to this new teaching and learning mode. This paper will focus on the interface design of webbased educational platforms for students and teachers from elementary and middle schools. The age of students from elementary and middle schools typically ranges from 5 to 13 years old. Their computer literacy level is still preliminary. So traditional online teaching platforms may not be appropriate for them. The design of learning systems …

Go to article

Expertise Style Transfer: A New Task Towards Better Communication Between Experts And Laymen, Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Lu, Tat-Seng Chua Jul 2020

Expertise Style Transfer: A New Task Towards Better Communication Between Experts And Laymen, Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Lu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving this task not only simplifies the professional language, but also improves the accuracy and expertise level of laymen descriptions using simple words. This is a challenging task, unaddressed in previous work, as it requires the models to have expert intelligence in order to modify text with a deep understanding of domain knowledge and structures. We establish the benchmark performance of five state-of-the-art models for style …

Go to article

Improving Event Detection Via Open-Domain Event Trigger Knowledge, Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie Jul 2020

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.

Go to article

Tree-Augmented Cross-Modal Encoding For Complex-Query Video Retrieval, Xun Yang, Jianfeng Dong, Yixin Cao, Xun Wang, Meng Wang, Tat-Seng Chua Jul 2020

Tree-Augmented Cross-Modal Encoding For Complex-Query Video Retrieval, Xun Yang, Jianfeng Dong, Yixin Cao, Xun Wang, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate …

Go to article

Deep Learning Of Facial Embeddings And Facial Landmark Points For The Detection Of Academic Emotions, Hua Leong Fwa Jul 2020

Deep Learning Of Facial Embeddings And Facial Landmark Points For The Detection Of Academic Emotions, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Automatic emotion recognition is an actively researched area as emotion plays a pivotal role in effective human communications. Equipping a computer to understand and respond to human emotions has potential applications in many fields including education, medicine, transport and hospitality. In a classroom or online learning context, the basic emotions do not occur frequently and do not influence the learning process itself. The academic emotions such as engagement, frustration, confusion and boredom are the ones which are pivotal to sustaining the motivation of learners. In this study, we evaluated the use of deep learning on FaceNet embeddings and facial landmark …

Go to article

A Review On Eye-Tracking Metrics For Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah Jul 2020

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.

Go to article

Disparity-Aware Domain Adaptation In Stereo Image Restoration, Bo Yan, Chenxi Ma, Bahetiyaer Bare, Weimin Tan, Steven C. H. Hoi Jun 2020

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) …

Go to article

Mnemonics Training: Multi-Class Incremental Learning Without Forgetting, Yaoyao Liu, Yuting Su, An-An Liu, Bernt Schiele, Qianru Sun Jun 2020

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 …

Go to article

Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai Jun 2020

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 …

Go to article

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. Jun 2020

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 …

Go to article

Hyperbolic Visual Embedding Learning For Zero-Shot Recognition, Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang Jun 2020

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 …

Go to article

Transferring And Regularizing Prediction For Semantic Segmentation, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Dong Liu, Tao Mei Jun 2020

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 …

Go to article

Cookgan: Causality Based Text-To-Image Synthesis, Bin Zhu, Chong-Wah Ngo Jun 2020

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 …

Go to article

Exploring Category-Agnostic Clusters For Open-Set Domain Adaptation, Yingwei Pan, Ting Yao, Yehao Li, Chong-Wah Ngo, Tao Mei Jun 2020

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 …

Go to article

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 Jun 2020

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, …

Go to article

Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun Jun 2020

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 …

Go to article

Visual Commonsense Representation Learning Via Causal Inference, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun Jun 2020

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 …

Go to article

Relationships Between Willingness To Share Information For Benefits And Trust, Gaurav Bansal, Fiona Fui-Hoon Nah May 2020

Relationships Between Willingness To Share Information For Benefits And Trust, Gaurav Bansal, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

This research examines the role of willingness to share one’s information for three benefits as tradeoffs – monetary gains, personalization, and national security – and their effects on trust in online businesses. Data were gathered from MTurk and the results indicate that willingness to share information for monetary gains and personalization is marginally associated with trust in online businesses, but willingness to share information for national security has no association with trust in online businesses. The paper also discusses implications, limitations, and future research directions.

Go to article

Assistance For Target Selection In Mobile Augmented Reality, Vinod Asokan, Scott Bateman, Anthony Tang May 2020

Assistance For Target Selection In Mobile Augmented Reality, Vinod Asokan, Scott Bateman, Anthony Tang

Research Collection School Of Computing and Information Systems

Mobile augmented reality - where a mobile device is used to view and interact with virtual objects displayed in the real world - is becoming more common. Target selection is the main method of interaction in mobile AR, but is particularly difficult because targets in AR can have challenging characteristics such as being moving or occluded (by digital or real world objects). Because target selection is particularly difficult and error prone in mobile AR, we conduct a comparative study of target assistance techniques. We compared four different cursor-based selection techniques against the standard touch-to-select interaction, finding that a newly adapted …

Go to article

Starhopper: A Touch Interface For Remote Object-Centric Drone Navigation, Jiannan Li, Ravin Balakrishnan, Tovi Grossman May 2020

Starhopper: A Touch Interface For Remote Object-Centric Drone Navigation, Jiannan Li, Ravin Balakrishnan, Tovi Grossman

Research Collection School Of Computing and Information Systems

Camera drones, a rapidly emerging technology, offer people the ability to remotely inspect an environment with a high degree of mobility and agility. However, manual remote piloting of a drone is prone to errors. In contrast, autopilot systems can require a significant degree of environmental knowledge and are not necessarily designed to support flexible visual inspections. Inspired by camera manipulation techniques in interactive graphics, we designed StarHopper, a novel touch screen interface for efficient object-centric camera drone navigation, in which a user directly specifies the navigation of a drone camera relative to a specified object of interest. The system relies …

Go to article

Use Of Eye-Tracking To Identify Psychological Indicators Of Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah, Matthew Thimgan May 2020

Use Of Eye-Tracking To Identify Psychological Indicators Of Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah, Matthew Thimgan

Research Collection School Of Computing and Information Systems

Sleepiness or sleep deprivation creates a serious hazard or obstacle to task execution and performance. Sleep deprivation can be life-threating (e.g., when driving or executing attention-critical tasks). We are interested to examine if eye-tracking technology can be used to assess and detect sleepiness in an online environment. In this research proposal, we will focus on examining the relationships between sleepiness and parameters involving pupil size, blinks, and saccades.

Go to article

Techniques To Visualize Occluded Graph Elements For 2.5d Map Editing, Kazuyuki Fujita, Daigo Hayashi, Kotaro Hara, Kazuki Takashima, Yoshifumi Kitamura Apr 2020

Techniques To Visualize Occluded Graph Elements For 2.5d Map Editing, Kazuyuki Fujita, Daigo Hayashi, Kotaro Hara, Kazuki Takashima, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

We propose an interface with two novel techniques to visualize occluded graph nodes and edges that help the user edit map data with a 2.5D geographical structure (e.g., multi-floor indoor maps). We first design a visualization technique —Repel Signification— that employs micro-animation to signify the graph elements that are overlapping with each other (and potentially erroneous). We also design a technique that enables the user to edit the occluded components with Expansion Interaction, which simultaneously visualizes both in-floor and across-floor occluded connections between the map elements. The combination of the two methods would enable the map editors (non-experts) to effectively …

Go to article

Dfseer: A Visual Analytics Approach To Facilitate Model Selection For Demand Forecasting, Dong Sun, Zezheng Feng, Yuanzhe Chen, Yong Wang, Jia Zeng, Mingxuan Yuan, Ting-Chuen Pong, Huamin Qu Apr 2020

Dfseer: A Visual Analytics Approach To Facilitate Model Selection For Demand Forecasting, Dong Sun, Zezheng Feng, Yuanzhe Chen, Yong Wang, Jia Zeng, Mingxuan Yuan, Ting-Chuen Pong, Huamin Qu

Research Collection School Of Computing and Information Systems

Selecting an appropriate model to forecast product demand is critical to the manufacturing industry. However, due to the data complexity, market uncertainty and users’ demanding requirements for the model, it is challenging for demand analysts to select a proper model. Although existing model selection methods can reduce the manual burden to some extent, they often fail to present model performance details on individual products and reveal the potential risk of the selected model. This paper presents DFSeer, an interactive visualization system to conduct reliable model selection for demand forecasting based on the products with similar historical demand. It supports model …

Go to article

Poster Abstract: Data Communication Using Switchable Privacy Glass, Changshuo Hu, Dong Ma, Mahbub Hassan, Wen Hu Apr 2020

Poster Abstract: Data Communication Using Switchable Privacy Glass, Changshuo Hu, Dong Ma, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

Switchable privacy glass can electronically change its state between opaque and transparent. In this work, we propose to exploit the electronic configurability of switchable glass to modulate natural light, which can be demodulated by a nearby receiver with light sensing capability to realise data communication over natural light. A key advantage is that no energy is used to generate light, as it simply modulates the existing light in the nature. We demonstrate that the proposed data communication using switchable glass modulation can achieve 33.33 bits per second communication with a bit rate below 1% under a wide range of ambient …

Go to article

Reinforced Negative Sampling Over Knowledge Graph For Recommendation, Xiang Wang, Yaokun Xu, Xiangnan He, Yixin Cao, Meng Wang, Tat-Seng Chua Apr 2020

Reinforced Negative Sampling Over Knowledge Graph For Recommendation, Xiang Wang, Yaokun Xu, Xiangnan He, Yixin Cao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples — both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy …

Go to article

Image Enhanced Event Detection In News Articles, Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juaizi Li, Lei Hou, Tat-Seng Chua Feb 2020

Image Enhanced Event Detection In News Articles, Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juaizi Li, Lei Hou, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event detection is a crucial and challenging sub-task of event extraction, which suffers from a severe ambiguity issue of trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe that images not only reflect the core events of the text, but are also helpful for the disambiguation of trigger words. In this paper, we first contribute an image dataset supplement to ED benchmarks (i.e., ACE2005) for training and evaluation. We then propose a novel Dual Recurrent Multimodal Model, DRMM, to conduct …

Go to article

Example-Based Colourization Via Dense Encoding Pyramids, Chufeng Xiao, Chu Han, Zhuming Zhang, Jing Qin, Tien-Tsin Wong, Guoqiang Han, Shengfeng He Feb 2020

Example-Based Colourization Via Dense Encoding Pyramids, Chufeng Xiao, Chu Han, Zhuming Zhang, Jing Qin, Tien-Tsin Wong, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi-scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both …

Go to article

Zero-Shot Ingredient Recognition By Multi-Relational Graph Convolutional Network, Jingjing Chen, Liangming Pan, Zhipeng Wei, Xiang Wang, Chong-Wah Ngo, Tat-Seng Chua Feb 2020

Zero-Shot Ingredient Recognition By Multi-Relational Graph Convolutional Network, Jingjing Chen, Liangming Pan, Zhipeng Wei, Xiang Wang, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recognizing ingredients for a given dish image is at the core of automatic dietary assessment, attracting increasing attention from both industry and academia. Nevertheless, the task is challenging due to the difficulty of collecting and labeling sufficient training data. On one hand, there are hundred thousands of food ingredients in the world, ranging from the common to rare. Collecting training samples for all of the ingredient categories is difficult. On the other hand, as the ingredient appearances exhibit huge visual variance during the food preparation, it requires to collect the training samples under different cooking and cutting methods for robust …

Go to article

Gdface: Gated Deformation For Multi-View Face Image Synthesis, Xuemiao Xu, Keke Li, Cheng Xu, Shengfeng He Feb 2020

Gdface: Gated Deformation For Multi-View Face Image Synthesis, Xuemiao Xu, Keke Li, Cheng Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Photorealistic multi-view face synthesis from a single image is an important but challenging problem. Existing methods mainly learn a texture mapping model from the source face to the target face. However, they fail to consider the internal deformation caused by the change of poses, leading to the unsatisfactory synthesized results for large pose variations. In this paper, we propose a Gated Deformable Face Synthesis Network to model the deformation of faces that aids the synthesis of the target face image. Specifically, we propose a dual network that consists of two modules. The first module estimates the deformation of two views …

Go to article

First Prev Next Last