Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 25 of 25
Full-Text Articles in Physical Sciences and Mathematics
Partial Annotation-Based Video Moment Retrieval Via Iterative Learning, Wei Ji, Renjie Liang, Lizi Liao, Hao Fei, Fuli Feng
Partial Annotation-Based Video Moment Retrieval Via Iterative Learning, Wei Ji, Renjie Liang, Lizi Liao, Hao Fei, Fuli Feng
Research Collection School Of Computing and Information Systems
Given a descriptive language query, Video Moment Retrieval (VMR) aims to seek the corresponding semantic-consistent moment clip in the video, which is represented as a pair of the start and end timestamps. Although current methods have achieved satisfying performance, training these models heavily relies on the fully-annotated VMR datasets. Nonetheless, precise video temporal annotations are extremely labor-intensive and ambiguous due to the diverse preferences of different annotators.Although there are several works trying to explore weakly supervised VMR tasks with scattered annotated frames as labels, there is still much room to improve in terms of accuracy. Therefore, we design a new …
Deep Weakly-Supervised Anomaly Detection, Guansong Pang, Chunhua Shen, Huidong Jin, Anton Van Den Hengel
Deep Weakly-Supervised Anomaly Detection, Guansong Pang, Chunhua Shen, Huidong Jin, Anton Van Den Hengel
Research Collection School Of Computing and Information Systems
Recent semi-supervised anomaly detection methods that are trained using small labeled anomaly examples and large unlabeled data (mostly normal data) have shown largely improved performance over unsupervised methods. However, these methods often focus on fitting abnormalities illustrated by the given anomaly examples only (i.e., seen anomalies), and consequently they fail to generalize to those that are not, i.e., new types/classes of anomaly unseen during training. To detect both seen and unseen anomalies, we introduce a novel deep weakly-supervised approach, namely Pairwise Relation prediction Network (PReNet), that learns pairwise relation features and anomaly scores by predicting the relation of any two …
Plan-And-Solve Prompting: Improving Zero-Shot Chain-Of-Thought Reasoning By Large Language Models, Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, Ee-Peng Lim
Plan-And-Solve Prompting: Improving Zero-Shot Chain-Of-Thought Reasoning By Large Language Models, Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zeroshot-CoT concatenates the target problem statement with “Let’s think step by step” as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation errors, missing-step errors, and semantic misunderstanding errors. To address the missing-step errors, we propose Planand-Solve (PS) Prompting. It …
Few-Shot Event Detection: An Empirical Study And A Unified View, Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun
Few-Shot Event Detection: An Empirical Study And A Unified View, Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun
Research Collection School Of Computing and Information Systems
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline. For fair evaluation, we compare 12 representative methods on three datasets, which are roughly grouped into prompt-based and prototype-based models for detailed analysis. Experiments consistently demonstrate that prompt-based methods, including ChatGPT, still significantly trail prototype-based methods in terms of overall performance. To investigate their superior performance, we break down their design elements along …
Heart: Motion-Resilient Heart Rate Monitoring With In-Ear Microphones, Kayla-Jade Butkow, Ting Dang, Andrea Ferlini, Dong Ma, Mascolo
Heart: Motion-Resilient Heart Rate Monitoring With In-Ear Microphones, Kayla-Jade Butkow, Ting Dang, Andrea Ferlini, Dong Ma, Mascolo
Research Collection School Of Computing and Information Systems
With the soaring adoption of in-ear wearables, the research community has started investigating suitable in-ear heart rate (HR) detection systems. HR is a key physiological marker of cardiovascular health and physical fitness. Continuous and reliable HR monitoring with wearable devices has therefore gained increasing attention in recent years. Existing HR detection systems in wearables mainly rely on photoplethysmography (PPG) sensors, however, these are notorious for poor performance in the presence of human motion. In this work, leveraging the occlusion effect that enhances low-frequency bone-conducted sounds in the ear canal, we investigate for the first time in-ear audio-based motion-resilient HR monitoring. …
Co-Advise: Cross Inductive Bias Distillation, Sucheng Ren, Zhengqi Gao, Tiany Hua, Zihui Xue, Yonglong Tian, Shengfeng He, Hang Zhao
Co-Advise: Cross Inductive Bias Distillation, Sucheng Ren, Zhengqi Gao, Tiany Hua, Zihui Xue, Yonglong Tian, Shengfeng He, Hang Zhao
Research Collection School Of Computing and Information Systems
The inductive bias of vision transformers is more relaxed that cannot work well with insufficient data. Knowledge distillation is thus introduced to assist the training of transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, in this paper, we delve into the influence of models inductive biases in knowledge distillation (e.g., convolution and involution). Our key observation is that the teacher accuracy is not the dominant reason for the student accuracy, but the teacher inductive bias is more important. We demonstrate that lightweight teachers with different architectural inductive biases can be used to co-advise the student transformer with …
Learning From The Master: Distilling Cross-Modal Advanced Knowledge For Lip Reading, Sucheng Ren, Yong Du, Jianming Lv, Guoqiang Han, Shengfeng He
Learning From The Master: Distilling Cross-Modal Advanced Knowledge For Lip Reading, Sucheng Ren, Yong Du, Jianming Lv, Guoqiang Han, Shengfeng He
Research Collection School Of Computing and Information Systems
Lip reading aims to predict the spoken sentences from silent lip videos. Due to the fact that such a vision task usually performs worse than its counterpart speech recognition, one potential scheme is to distill knowledge from a teacher pretrained by audio signals. However, the latent domain gap between the cross-modal data could lead to a learning ambiguity and thus limits the performance of lip reading. In this paper, we propose a novel collaborative framework for lip reading, and two aspects of issues are considered: 1) the teacher should understand bi-modal knowledge to possibly bridge the inherent cross-modal gap; 2) …
A Performance-Sensitive Malware Detection System Using Deep Learning On Mobile Devices, Ruitao Feng, Sen Chen, Xiaofei Xie, Guozhu Meng, Shang-Wei Lin, Yang Liu
A Performance-Sensitive Malware Detection System Using Deep Learning On Mobile Devices, Ruitao Feng, Sen Chen, Xiaofei Xie, Guozhu Meng, Shang-Wei Lin, Yang Liu
Research Collection School Of Computing and Information Systems
Currently, Android malware detection is mostly performed on server side against the increasing number of malware. Powerful computing resource provides more exhaustive protection for app markets than maintaining detection by a single user. However, apart from the applications (apps) provided by the official market (i.e., Google Play Store), apps from unofficial markets and third-party resources are always causing serious security threats to end-users. Meanwhile, it is a time-consuming task if the app is downloaded first and then uploaded to the server side for detection, because the network transmission has a lot of overhead. In addition, the uploading process also suffers …
Empirical Study Of Usage And Performance Of Java Collections, Diego Costa, Artur Andrzejak, Janos Seboek, David Lo
Empirical Study Of Usage And Performance Of Java Collections, Diego Costa, Artur Andrzejak, Janos Seboek, David Lo
Research Collection School Of Computing and Information Systems
Collection data structures have a major impact on the performance of applications, especially in languages such as Java, C#, or C++. This requires a developer to select an appropriate collection from a large set of possibilities, including different abstractions (e.g. list, map, set, queue), and multiple implementations. In Java, the default implementation of collections is provided by the standard Java Collection Framework (JCF). However, there exist a large variety of less known third-party collection libraries which can provide substantial performance benefits with minimal code changes.
A Survey On Wireless Indoor Localization From The Device Perspective, Jiang Xiao, Zimu Zhou, Youwen Yi, Lionel M. Ni
A Survey On Wireless Indoor Localization From The Device Perspective, Jiang Xiao, Zimu Zhou, Youwen Yi, Lionel M. Ni
Research Collection School Of Computing and Information Systems
With the marvelous development of wireless techniques and ubiquitous deployment of wireless systems indoors, myriad indoor location-based services (ILBSs) have permeated into numerous aspects of modern life. The most fundamental functionality is to pinpoint the location of the target via wireless devices. According to how wireless devices interact with the target, wireless indoor localization schemes roughly fall into two categories: device based and device free. In device-based localization, a wireless device (e.g., a smartphone) is attached to the target and computes its location through cooperation with other deployed wireless devices. In device-free localization, the target carries no wireless devices, while …
The Effects Of Multiple Query Evidences On Social Image Retrieval, Zhiyong Cheng, Jialie Shen, Haiyan Miao
The Effects Of Multiple Query Evidences On Social Image Retrieval, Zhiyong Cheng, Jialie Shen, Haiyan Miao
Research Collection School Of Computing and Information Systems
System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo …
Opinion Question Answering By Sentiment Clip Localization, Lei Pang, Chong-Wah Ngo
Opinion Question Answering By Sentiment Clip Localization, Lei Pang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
This article considers multimedia question answering beyond factoid and how-to questions. We are interested in searching videos for answering opinion-oriented questions that are controversial and hotly debated. Examples of questions include "Should Edward Snowden be pardoned?" and "Obamacare-unconstitutional or not?". These questions often invoke emotional response, either positively or negatively, hence are likely to be better answered by videos than texts, due to the vivid display of emotional signals visible through facial expression and speaking tone. Nevertheless, a potential answer of duration 60s may be embedded in a video of 10min, resulting in degraded user experience compared to reading the …
Negative Factor: Improving Regular-Expression Matching In Strings, Xiaochun Yang, Tao Qiu, Bin Wang, Baihua Zheng, Yaoshu Wang, Chen Li
Negative Factor: Improving Regular-Expression Matching In Strings, Xiaochun Yang, Tao Qiu, Bin Wang, Baihua Zheng, Yaoshu Wang, Chen Li
Research Collection School Of Computing and Information Systems
The problem of finding matches of a regular expression (RE) on a string exists in many applications such as text editing, biosequence search, and shell commands. Existing techniques first identify candidates using substrings in the RE, then verify each of them using an automaton. These techniques become inefficient when there are many candidate occurrences that need to be verified. In this paper we propose a novel technique that prunes false negatives by utilizing negative factors, which are substrings that cannot appear in an answer. A main advantage of the technique is that it can be integrated with many existing algorithms …
A Hamming Embedding Kernel With Informative Bag-Of-Visual Words For Video Semantic Indexing, Feng Wang, Wen-Lei Zhao, Chong-Wah Ngo, Bernard Merialdo
A Hamming Embedding Kernel With Informative Bag-Of-Visual Words For Video Semantic Indexing, Feng Wang, Wen-Lei Zhao, Chong-Wah Ngo, Bernard Merialdo
Research Collection School Of Computing and Information Systems
In this article, we propose a novel Hamming embedding kernel with informative bag-of-visual words to address two main problems existing in traditional BoW approaches for video semantic indexing. First, Hamming embedding is employed to alleviate the information loss caused by SIFT quantization. The Hamming distances between keypoints in the same cell are calculated and integrated into the SVM kernel to better discriminate different image samples. Second, to highlight the concept-specific visual information, we propose to weight the visual words according to their informativeness for detecting specific concepts. We show that our proposed kernels can significantly improve the performance of concept …
Fundamental Limits On End-To-End Throughput Of Network Coding In Multi-Rate And Multicast Wireless Networks, Luiz Felipe Viera, Mario Gerla, Archan Misra
Fundamental Limits On End-To-End Throughput Of Network Coding In Multi-Rate And Multicast Wireless Networks, Luiz Felipe Viera, Mario Gerla, Archan Misra
Research Collection School Of Computing and Information Systems
This paper investigates the interaction between network coding and link-layer transmission rate diversity in multi-hop wireless networks. By appropriately mixing data packets at intermediate nodes, network coding allows a single multicast flow to achieve higher throughput to a set of receivers. Broadcast applications can also exploit link-layer rate diversity, whereby individual nodes can transmit at faster rates at the expense of corresponding smaller coverage area. We first demonstrate how combining rate-diversity with network coding can provide a larger capacity for data dissemination of a single multicast flow, and how consideration of rate diversity is critical for maximizing system throughput. Next …
Efficient Index-Based Approaches For Skyline Queries In Location-Based Applications, Ken C. K. Lee, Baihua Zheng, Cindy Chen, Chi-Yin Chow
Efficient Index-Based Approaches For Skyline Queries In Location-Based Applications, Ken C. K. Lee, Baihua Zheng, Cindy Chen, Chi-Yin Chow
Research Collection School Of Computing and Information Systems
Enriching many location-based applications, various new skyline queries are proposed and formulated based on the notion of locational dominance, which extends conventional one by taking objects' nearness to query positions into account additional to objects' nonspatial attributes. To answer a representative class of skyline queries for location-based applications efficiently, this paper presents two index-based approaches, namely, augmented R-tree and dominance diagram. Augmented R-tree extends R-tree by including aggregated nonspatial attributes in index nodes to enable dominance checks during index traversal. Dominance diagram is a solution-based approach, by which each object is associated with a precomputed nondominance scope wherein query points …
On Effects Of Visual Query Complexity, Jialie Shen, Cheng Zhiyong
On Effects Of Visual Query Complexity, Jialie Shen, Cheng Zhiyong
Research Collection School Of Computing and Information Systems
As an effective technique to manage large scale image collections, content-based image retrieval (CBIR) has been received great attentions and became a very active research domain in recent years. While assessing system performance is one of the key factors for the related technological advancement, relatively little attention has been paid to model and analyze test queries. This paper documents a study on the problem of determining visual query complexity as a measure for predicting image retrieval performance. We propose a quantitative metric for measuring complexity of image queries for content-based image search engine. A set of experiments are carried out …
Multimedia Recommendation: Technology And Techniques, Jialie Shen, Meng Wang, Shuicheng Yan, Peng Cui
Multimedia Recommendation: Technology And Techniques, Jialie Shen, Meng Wang, Shuicheng Yan, Peng Cui
Research Collection School Of Computing and Information Systems
In recent years, we have witnessed a rapid growth in the availability of digital multimedia on various application platforms and domains. Consequently, the problem of information overload has become more and more serious. In order to tackle the challenge, various multimedia recommendation technologies have been developed by different research communities (e.g., multimedia systems, information retrieval, machine learning and computer version). Meanwhile, many commercial web systems (e.g., Flick, YouTube, and Last.fm) have successfully applied recommendation techniques to provide users personalized content and services in a convenient and flexible way. When looking back, the information retrieval (IR) community has a long history …
Business Intelligence And Analytics: Research Directions, Ee Peng Lim, Hsinchun Chen, Guoqing Chen
Business Intelligence And Analytics: Research Directions, Ee Peng Lim, Hsinchun Chen, Guoqing Chen
Research Collection School Of Computing and Information Systems
Business intelligence and analytics (BIA) is about the development of technologies, systems, practices, and applications to analyze critical business data so as to gain new insights about business and markets. The new insights can be used for improving products and services, achieving better operational efficiency, and fostering customer relationships. In this article, we will categorize BIA research activities into three broad research directions: (a) big data analytics, (b) text analytics, and (c) network analytics. The article aims to review the state-of-the-art techniques and models and to summarize their use in BIA applications. For each research direction, we will also determine …
Searching Patterns For Relation Extraction Over The Web: Rediscovering The Pattern-Relation Duality, Yuan Fang, Kevin Chen-Chuan Chang
Searching Patterns For Relation Extraction Over The Web: Rediscovering The Pattern-Relation Duality, Yuan Fang, Kevin Chen-Chuan Chang
Research Collection School Of Computing and Information Systems
While tuple extraction for a given relation has been an active research area, its dual problem of pattern search- to find and rank patterns in a principled way- has not been studied explicitly. In this paper, we propose and address the problem of pattern search, in addition to tuple extraction. As our objectives, we stress reusability for pattern search and scalability of tuple extraction, such that our approach can be applied to very large corpora like the Web. As the key foundation, we propose a conceptual model PRDualRank to capture the notion of precision and recall for both tuples and …
Accelerating Near-Duplicate Video Matching By Combining Visual Similarity And Alignment Distortion, Hung-Khoon Tan, Xiao Wu, Chong-Wah Ngo, Wan-Lei Zhao
Accelerating Near-Duplicate Video Matching By Combining Visual Similarity And Alignment Distortion, Hung-Khoon Tan, Xiao Wu, Chong-Wah Ngo, Wan-Lei Zhao
Research Collection School Of Computing and Information Systems
In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplicate videos typically follow certain spatial arrangements, such property could be employed to guide the alignment of two keyframe sequences. We set the alignment problem as an integer quadratic programming problem, where the cost function takes into account both the visual similarity of the corresponding keyframes as well as the alignment distortion among the set of correspondences. The set of keyframe-pairs found …
Modeling Video Hyperlinks With Hypergraph For Web Video Reranking, Hung-Khoon Tan, Chong-Wah Ngo, Xiao Wu
Modeling Video Hyperlinks With Hypergraph For Web Video Reranking, Hung-Khoon Tan, Chong-Wah Ngo, Xiao Wu
Research Collection School Of Computing and Information Systems
In this paper, we investigate a novel approach of exploiting visual-duplicates for web video reranking using hypergraph. Current graph-based reranking approaches consider mainly the pair-wise linking of keyframes and ignore reliability issues that are inherent in such representation. We exploit higher order relation to overcome the issues of missing links in visual-duplicate keyframes and in addition identify the latent relationships among keyframes. Based on hypergraph, we consider two groups of video threads: visual near-duplicate threads and story threads, to hyperlink web videos and describe the higher order information existing in video content. To facilitate reranking using random walk algorithm, the …
An Effective Approach To 3d Deformable Surface Tracking, Jianke Zhu, Steven C. H. Hoi, Zenglin Xu, Michael R. Lyu
An Effective Approach To 3d Deformable Surface Tracking, Jianke Zhu, Steven C. H. Hoi, Zenglin Xu, Michael R. Lyu
Research Collection School Of Computing and Information Systems
The key challenge with 3D deformable surface tracking arises from the difficulty in estimating a large number of 3D shape parameters from noisy observations. A recent state-of-the-art approach attacks this problem by formulating it as a Second Order Cone Programming (SOCP) feasibility problem. The main drawback of this solution is the high computational cost. In this paper, we first reformulate the problem into an unconstrained quadratic optimization problem. Instead of handling a large set of complicated SOCP constraints, our new formulation can be solved very efficiently by resolving a set of sparse linear equations. Based on the new framework, a …
Performance Sensitivity And Fairness Of Ecn-Aware 'Modified Tcp', Archan Misra, Teunis Ott
Performance Sensitivity And Fairness Of Ecn-Aware 'Modified Tcp', Archan Misra, Teunis Ott
Research Collection School Of Computing and Information Systems
The paper discusses how Explicit Congestion Notification (ECN) can be used to devise a congestion control mechanism for the Internet, which is more rapidly reactive and allows best-effort flows to rapidly adjust to fluctuations in available capacity. Our ECN-mod protocol involves simple modifications to TCP behavior and leverages more aggressive marking-based router feedback.Simulations show that ECN-mod is better than TCP NewReno even for Web-style intermittent traffic sources, and makes the link utilization significantly less sensitive to the variation in the number of active flows. Simulations also show that, while ECN-mod flows obtain a larger portion of the available capacity than …
Performance Analysis Of Two Bridged Csma/Cd Networks, C. C. Ko, W. C. Wang, J. L. Du, Robert H. Deng, K. M. Lye
Performance Analysis Of Two Bridged Csma/Cd Networks, C. C. Ko, W. C. Wang, J. L. Du, Robert H. Deng, K. M. Lye
Research Collection School Of Computing and Information Systems
This paper analyses the performance of two non-persistent CSMA/CD LANs linked by a bridge. The main function of the bridge is to buffer all internet work packets and forward them across networks to their destinations. From establishing and solving the main equations governing the behaviour of the bridged networks, the effects of design parameters such as the bridge buffer size and re-transmission back off delay on the performance of the system are studied. It is shown that if these parameters are chosen properly, better throughput and delay performance can be obtained, when compared with an equivalent CSMA/CD network without using …