Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Software Engineering (42)
- Databases and Information Systems (33)
- Artificial Intelligence and Robotics (26)
- Numerical Analysis and Scientific Computing (14)
- Graphics and Human Computer Interfaces (12)
-
- Engineering (7)
- Information Security (7)
- OS and Networks (6)
- Computer Engineering (4)
- Social and Behavioral Sciences (4)
- Operations Research, Systems Engineering and Industrial Engineering (3)
- Programming Languages and Compilers (3)
- Business (2)
- Communication (2)
- Digital Communications and Networking (2)
- Education (2)
- Public Affairs, Public Policy and Public Administration (2)
- Social Media (2)
- Theory and Algorithms (2)
- Transportation (2)
- Computer and Systems Architecture (1)
- Educational Assessment, Evaluation, and Research (1)
- Educational Methods (1)
- Finance and Financial Management (1)
- Hardware Systems (1)
- Higher Education (1)
- Law (1)
- Law Enforcement and Corrections (1)
Articles 91 - 98 of 98
Full-Text Articles in Physical Sciences and Mathematics
Demo: Deepmon - Building Mobile Gpu Deep Learning Models For Continuous Vision Applications, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee
Demo: Deepmon - Building Mobile Gpu Deep Learning Models For Continuous Vision Applications, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee
Research Collection School Of Computing and Information Systems
Deep learning has revolutionized vision sensing applications in terms of accuracy comparing to other techniques. Its breakthrough comes from the ability to extract complex high level features directly from sensor data. However, deep learning models are still yet to be natively supported on mobile devices due to high computational requirements. In this paper, we present DeepMon, a next generation of DeepSense [1] framework, to enable deep learning models on conventional mobile devices (e.g. Samsung Galaxy S7) for continuous vision sensing applications. Firstly, Deep-Mon exploits similarity between consecutive video frames for intermediate data caching within models to enhance inference latency. Secondly, …
A Compare-Aggregate Model For Matching Text Sequences, Shuohang Wang, Jing Jiang
A Compare-Aggregate Model For Matching Text Sequences, Shuohang Wang, Jing Jiang
Research Collection School Of Computing and Information Systems
Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks. We particularly focus on the different comparison functions we can use to match two vectors. We use four different datasets to evaluate the model. We find that some simple comparison functions based on element-wise operations can work better than standard neural network and neural tensor network.
When A Friend Online Is More Than A Friend In Life: Intimate Relationship Prediction In Microblogs, Yunshi Lan, Mengqi Zhang, Feida Zhu, Jing Jiang, Ee-Peng Lim
When A Friend Online Is More Than A Friend In Life: Intimate Relationship Prediction In Microblogs, Yunshi Lan, Mengqi Zhang, Feida Zhu, Jing Jiang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Microblogging services such as Twitter and Sina Weibo have been an important, if not indespensible, platform for people around the world to connect to one another. The rich content and user interactions on these platforms reveal insightful information about each user that are valuable for various real-life applications. In particular, user offline relationships, especially those intimate ones such as family members and couples, offer distinctive value for many business and social settings. In this study, we focus on using Sina Weibo to discover intimate offline relationships among users. The problem is uniquely interesting and challenging due to the difficulty in …
Deepsense: A Gpu-Based Deep Convolutional Neural Network Framework On Commodity Mobile Devices, Huynh Nguyen Loc, Rajesh Krishna Balan, Youngki Lee
Deepsense: A Gpu-Based Deep Convolutional Neural Network Framework On Commodity Mobile Devices, Huynh Nguyen Loc, Rajesh Krishna Balan, Youngki Lee
Research Collection School Of Computing and Information Systems
Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to …
Demo: Gpu-Based Image Recognition And Object Detection On Commodity Mobile Devices, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee
Demo: Gpu-Based Image Recognition And Object Detection On Commodity Mobile Devices, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee
Research Collection School Of Computing and Information Systems
In this demo, we show that it is feasible to execute CNN for vision sensing tasks directly on mobile devices by leveraging integrated GPU. We propose our design of DeepSense framework based on OpenCL to execute deep learning algorithms in energy-efficient and fast manner.
Supercnn: A Superpixelwise Convolutional Neural Network For Salient Object Detection, Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang
Supercnn: A Superpixelwise Convolutional Neural Network For Salient Object Detection, Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang
Research Collection School Of Computing and Information Systems
Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which …
Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li
Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li
Research Collection School Of Computing and Information Systems
Learning effective feature representations and similarity measures are crucial to the retrieval performance of a content-based image retrieval (CBIR) system. Despite extensive research efforts for decades, it remains one of the most challenging open problems that considerably hinders the successes of real-world CBIR systems. The key challenge has been attributed to the well-known "semantic gap" issue that exists between low-level image pixels captured by machines and high-level semantic concepts perceived by human. Among various techniques, machine learning has been actively investigated as a possible direction to bridge the semantic gap in the long term. Inspired by recent successes of deep …
Online Multimodal Distance Metric Learning With Application To Image Retrieval, Pengcheng Wu, Steven C. H. Hoi, Hao Xia, Peilin Zhao, Dayong Wang, Chunyan Miao
Online Multimodal Distance Metric Learning With Application To Image Retrieval, Pengcheng Wu, Steven C. H. Hoi, Hao Xia, Peilin Zhao, Dayong Wang, Chunyan Miao
Research Collection School Of Computing and Information Systems
Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance function on the input feature space, in which the assumption of linearity limits their capacity of measuring the similarity on complex patterns in real-world applications; (ii) they are often designed for learning distance metrics on uni-modal data, which may not effectively handle the similarity measures for multimedia objects with multimodal representations. To address these limitations, in this paper, we …