Physical Sciences and Mathematics Commons^™

Deep Learning For Real-World Object Detection, Xiongwei Wu

Dissertations and Theses Collection (Open Access)

Despite achieving significant progresses, most existing detectors are designed to detect objects in academic contexts but consider little in real-world scenarios. In real-world applications, the scale variance of objects can be significantly higher than objects in academic contexts; In addition, existing methods are designed for achieving localization with relatively low precision, however more precise localization is demanded in real-world scenarios; Existing methods are optimized with huge amount of annotated data, but in certain real-world scenarios, only a few samples are available. In this dissertation, we aim to explore novel techniques to address these research challenges to make object detection algorithms …

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 …

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 …

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.

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 …

Probabilistic Value Selection For Space Efficient Model, Gunarto Sindoro Njoo, Baihua Zheng, Kuo-Wei Hsu, Wen-Chih Peng

Research Collection School Of Computing and Information Systems

An alternative to current mainstream preprocessing methods is proposed: Value Selection (VS). Unlike the existing methods such as feature selection that removes features and instance selection that eliminates instances, value selection eliminates the values (with respect to each feature) in the dataset with two purposes: reducing the model size and preserving its accuracy. Two probabilistic methods based on information theory's metric are proposed: PVS and P + VS. Extensive experiments on the benchmark datasets with various sizes are elaborated. Those results are compared with the existing preprocessing methods such as feature selection, feature transformation, and instance selection methods. Experiment results …

Improving Multimodal Named Entity Recognition Via Entity Span Detection With Unified Multimodal Transformer, Jianfei Yu, Jing Jiang, Li Yang, Rui Xia

Research Collection School Of Computing and Information Systems

In this paper, we study Multimodal Named Entity Recognition (MNER) for social media posts. Existing approaches for MNER mainly suffer from two drawbacks: (1) despite generating word-aware visual representations, their word representations are insensitive to the visual context; (2) most of them ignore the bias brought by the visual context. To tackle the first issue, we propose a multimodal interaction module to obtain both image-aware word representations and word-aware visual representations. To alleviate the visual bias, we further propose to leverage purely text-based entity span detection as an auxiliary module, and design a Unified Multimodal Transformer to guide the final …

Graph-To-Tree Learning For Solving Math Word Problems, Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well. This results in poor quantity representations and incorrect solution expressions. In this paper, we propose Graph2Tree, a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. Included in our Graph2Tree framework are two graphs, namely the Quantity Cell Graph and Quantity Comparison Graph, which are designed to address limitations of existing methods by …

Trajectory Similarity Learning With Auxiliary Supervision And Optimal Matching, Hanyuan Zhang, Xingyu Zhang, Qize Jiang, Baihua Zheng, Zhenbang Sun, Weiwei Sun, Changhu Wang

Research Collection School Of Computing and Information Systems

Trajectory similarity computation is a core problem in the field of trajectory data queries. However, the high time complexity of calculating the trajectory similarity has always been a bottleneck in real-world applications. Learning-based methods can map trajectories into a uniform embedding space to calculate the similarity of two trajectories with embeddings in constant time. In this paper, we propose a novel trajectory representation learning framework Traj2SimVec that performs scalable and robust trajectory similarity computation. We use a simple and fast trajectory simplification and indexing approach to obtain triplet training samples efficiently. We make the framework more robust via taking full …

Biane: Bipartite Attributed Network Embedding, Wentao Huang, Yuchen Li, Yuan Fang, Ju Fan, Hongxia Yang

Research Collection School Of Computing and Information Systems

Network embedding effectively transforms complex network data into a low-dimensional vector space and has shown great performance in many real-world scenarios, such as link prediction, node classification, and similarity search. A plethora of methods have been proposed to learn node representations and achieve encouraging results. Nevertheless, little attention has been paid on the embedding technique for bipartite attributed networks, which is a typical data structure for modeling nodes from two distinct partitions. In this paper, we propose a novel model called BiANE, short for Bipartite Attributed Network Embedding. In particular, BiANE not only models the inter-partition proximity but also models …

Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization With Nearly Optimal Generalization, Pan Zhou, Xiaotong Yuan

Research Collection School Of Computing and Information Systems

Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gradient complexity of SVRG-type algorithms usually scales linearly with data size and thus could still be expensive for huge data. To address this deficiency, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly-convex problems that enjoys provably improved data-size-independent complexity guarantees.

Geoprune: Efficiently Matching Trips In Ride-Sharing Through Geometric Properties, Yixin Xu, Jianzhong Qi, Renata Borovica-Gajic

Research Collection School Of Computing and Information Systems

On-demand ride-sharing is rapidly growing. Matching trip requests to vehicles efficiently is critical for the service quality of ride-sharing. To match trip requests with vehicles, a prune-And-select scheme is commonly used. The pruning stage identifies feasible vehicles that can satisfy the trip constraints (e.g., trip time). The selection stage selects the optimal one(s) from the feasible vehicles. The pruning stage is crucial to lowering the complexity of the selection stage and to achieve efficient matching. We propose an effective and efficient pruning algorithm called GeoPrune. GeoPrune represents the time constraints of trip requests using circles and ellipses, which can be …

Next-Term Grade Prediction: A Machine Learning Approach, Audrey Tedja Widjaja, Lei Wang, Nghia Truong Trong, Aldy Gunawan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

As students progress in their university programs, they have to face many course choices. It is important for them to receive guidance based on not only their interest, but also the "predicted" course performance so as to improve learning experience and optimise academic performance. In this paper, we propose the next-term grade prediction task as a useful course selection guidance. We propose a machine learning framework to predict course grades in a specific program term using the historical student-course data. In this framework, we develop the prediction model using Factorization Machine (FM) and Long Short Term Memory combined with FM …

Semi-Supervised Co-Clustering On Attributed Heterogeneous Information Networks, Yugang Ji, Chuan Shi, Yuan Fang, Xiangnan Kong, Mingyang Yin

Research Collection School Of Computing and Information Systems

Node clustering on heterogeneous information networks (HINs) plays an important role in many real-world applications. While previous research mainly clusters same-type nodes independently via exploiting structural similarity search, they ignore the correlations of different-type nodes. In this paper, we focus on the problem of co-clustering heterogeneous nodes where the goal is to mine the latent relevance of heterogeneous nodes and simultaneously partition them into the corresponding type-aware clusters. This problem is challenging in two aspects. First, the similarity or relevance of nodes is not only associated with multiple meta-path-based structures but also related to numerical and categorical attributes. Second, clusters …

Bridging Hierarchical And Sequential Context Modeling For Question-Driven Extractive Answer Summarization, Yang Deng, Wenxuan Zhang, Yaliang Li, Min Yang, Wai Lam, Ying Shen

Research Collection School Of Computing and Information Systems

Non-factoid question answering (QA) is one of the most extensive yet challenging application and research areas of retrieval-based question answering. In particular, answers to non-factoid questions can often be too lengthy and redundant to comprehend, which leads to the great demand on answer sumamrization in non-factoid QA. However, the multi-level interactions between QA pairs and the interrelation among different answer sentences are usually modeled separately on current answer summarization studies. In this paper, we propose a unified model to bridge hierarchical and sequential context modeling for question-driven extractive answer summarization. Specifically, we design a hierarchical compare-aggregate method to integrate the …

Towards An Optimal Outdoor Advertising Placement: When A Budget Constraint Meets Moving Trajectories, Ping Zhang, Zhifeng Bao, Yuchen Li, Guoliang Li, Yipeng Zhang, Zhiyong Peng

Research Collection School Of Computing and Information Systems

In this article, we propose and study the problem of trajectory-driven influential billboard placement: given a set of billboards U (each with a location and a cost), a database of trajectories T, and a budget L, we find a set of billboards within the budget to influence the largest number of trajectories. One core challenge is to identify and reduce the overlap of the influence from different billboards to the same trajectories, while keeping the budget constraint into consideration. We show that this problem is NP-hard and present an enumeration based algorithm with (1-1/e) approximation ratio. However, the enumeration would …

Answer Ranking For Product-Related Questions Via Multiple Semantic Relations Modeling, Wenxuan Zhang, Yang Deng, Wai Lam

Research Collection School Of Computing and Information Systems

Many E-commerce sites now offer product-specific question answering platforms for users to communicate with each other by posting and answering questions during online shopping. However, the multiple answers provided by ordinary users usually vary diversely in their qualities and thus need to be appropriately ranked for each question to improve user satisfaction. It can be observed that product reviews usually provide useful information for a given question, and thus can assist the ranking process. In this paper, we investigate the answer ranking problem for product-related questions, with the relevant reviews treated as auxiliary information that can be exploited for facilitating …

Interactive Entity Linking Using Entity-Word Representations, Pei Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

To leverage on entity and word semantics in entity linking, embedding models have been developed to represent entities, words and their context such that candidate entities for each mention can be determined and ranked accurately using their embeddings. To leverage on entity and word semantics in entity linking, embedding models have been developed to represent entities, words and their context such that candidate entities for each mention can be determined and ranked accurately using their embeddings. In this paper, we leverage on human intelligence for embedding-based interactive entity linking. We adopt an active learning approach to select mentions for human …

Keen2act: Activity Recommendation In Online Social Collaborative Platforms, Roy Ka-Wei Lee, Thong Hoang, Richard J. Oentaryo, David Lo

Research Collection School Of Computing and Information Systems

Social collaborative platforms such as GitHub and Stack Overflow have been increasingly used to improve work productivity via collaborative efforts. To improve user experiences in these platforms, it is desirable to have a recommender system that can suggest not only items (e.g., a GitHub repository) to a user, but also activities to be performed on the suggested items (e.g., forking a repository). To this end, we propose a new approach dubbed Keen2Act, which decomposes the recommendation problem into two stages: the Keen and Act steps. The Keen step identifies, for a given user, a (sub)set of items in which he/she …

Introduction To The R-Package: Usdampr, Elliott James Dennis, Bowen Chen

Extension Farm and Ranch Management News

Why the Need for the Package? In the 1990’s, concern over growing packer concentration and a hog industry market shock resulted in discontent among producers and packers. As a result, the United States Congress passed the Livestock Mandatory Reporting Act of 1999 (1999 Act) [Pub. L. 106-78, Title IX] which is required to be reauthorized every five years. See here for a full history of the Livestock Mandatory Reporting Background.

Market reports were publicly issued in the form of .txt files with varying frequency from April 2000 to April 2020. Current and historical data were also housed in a USDA-AMS …

Translating Counting Problems Into Computable Language Expressions, Zach Prescott

Theses

The realm of automated problem solving is a relatively new field, even in the context of natural language processing. One area where this is often demonstrated is that of creating a program that can solve word problems. The program must understand the problem, perform some processing, and then convey this information to a user in a way that is accessible and understandable. There has been quite a lot of progress in this area with simpler problems. However, when it comes to understanding problems that involve a level of NLP, the results are not conclusive. In this paper, we would like …

Mapping And Describing Geospatial Data To Generalize Complex Models: The Case Of Littosim-Gen, Ahmed Laatabi, Nicolas Becu, Nicolas Marilleau, Cécilia Pignon-Mussaud, Marion Amalric, Xavier Bertin, Brice Anselme, Elise Beck

International Journal of Geospatial and Environmental Research

For some scientific questions, empirical data are essential to develop reliable simulation models. These data usually come from different sources with diverse and heterogeneous formats. The design of complex data-driven models is often shaped by the structure of the data available in research projects. Hence, applying such models to other case studies requires either to get similar data or to transform new data to fit the model inputs. It is the case of agent-based models (ABMs) that use advanced data structures such as Geographic Information Systems data. We faced this problem in the LittoSIM-GEN project when generalizing our participatory flooding …

Context-Aware And Scale-Insensitive Temporal Repetition Counting, Huaidong Zhang, Xuemiao Xu, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Temporal repetition counting aims to estimate the number of cycles of a given repetitive action. Existing deep learning methods assume repetitive actions are performed in a fixed time-scale, which is invalid for the complex repetitive actions in real life. In this paper, we tailor a context-aware and scale-insensitive framework, to tackle the challenges in repetition counting caused by the unknown and diverse cycle-lengths. Our approach combines two key insights: (1) Cycle lengths from different actions are unpredictable that require large-scale searching, but, once a coarse cycle length is determined, the variety between repetitions can be overcome by regression. (2) Determining …

Adaptive Loss-Aware Quantization For Multi-Bit Networks, Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele

Research Collection School Of Computing and Information Systems

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ directly minimizes the quantizationinduced error on the loss function involving neither gradient approximation nor …

Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Fashion trend forecasting is a crucial task for both academia andindustry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal thereal fashion trends. Towards insightful fashion trend forecasting,this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Furthermore, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge Enhanced …

Maximum A Posteriori Estimation For Information Source Detection, Biao Chang, Enhong Chen, Feida Zhu, Qi Liu, Tong Xu

Research Collection School Of Computing and Information Systems

Information source detection is to identify nodes initiating the diffusion process in a network, which has a wide range of applications including epidemic outbreak prevention, Internet virus source identification, and rumor source tracing in social networks. Although it has attracted ever-increasing attention from research community in recent years, existing solutions still suffer from high time complexity and inadequate effectiveness, due to high dynamics of information diffusion and observing just a snapshot of the whole process. To this end, we present a comprehensive study for single information source detection in weighted graphs. Specifically, we first propose a maximum a posteriori (MAP) …

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 …

Secure Server-Aided Data Sharing Clique With Attestation, Yujue Wang, Hwee Hwa Pang, Robert H. Deng, Yong Ding, Qianhong Wu, Bo Qin, Kefeng Fan

Research Collection School Of Computing and Information Systems

In this paper, we consider the security issues in data sharing cliques via remote server. We present a public key re-encryption scheme with delegated equality test on ciphertexts (PRE-DET). The scheme allows users to share outsourced data on the server without performing decryption-then-encryption procedures, allows new users to dynamically join the clique, allows clique users to attest the message underlying a ciphertext, and enables the server to partition outsourced user data without any further help of users after being delegated. We introduce the PRE-DET framework, propose a concrete construction and formally prove its security against five types of adversaries regarding …

Goods Consumed During Transit In Split Delivery Vehicle Routing Problems: Modeling And Solution, Wenzhe Yang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

This article presents the modeling and solution of an extended type of split delivery vehicle routing problem (SDVRP). In SDVRP, the demands of customers need to be met by efficiently routing a given number of capacitated vehicles, wherein each customer may be served multiple times by more than one vehicle. Furthermore, in many real-world scenarios, consumption of vehicles en route is the same as the goods being delivered to customers, such as food, water and fuel in rescue or replenishment missions in harsh environments. Moreover, the consumption may also be in virtual forms, such as time spent in constrained tasks. …

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 …