Object Detection in Aerial Images : A Large-Scale Benchmark and Challenges

In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the…

Recombination Rate Analysis of InGaN-Based Red-Emitting Light-Emitting Diodes

The recombination rates are measured and analyzed for red-emitting InGaN light-emitting diodes (LEDs) to better understand the factors that limit their efficiency. InGaN/AlGaN/GaN multiple quantum …

Evolutionary Sequential Transfer Optimization for Objective-Heterogeneous Pro…

Evolutionary sequential transfer optimization is a paradigm that leverages search experience from solved source optimization tasks to accelerate the evolutionary search of a target task. Even thoug…

Unmixing Convolutional Features for Crisp Edge Detection

This article presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is ma…

Recombination Rates of InxGa1−xN/AlyGa1−yN/GaN Multiple Quantum Wells Emi…

The recombination rates in an In 0.25 Ga 0.75 N/Al 0.48 Ga 0.52 N/GaN multiple quantum well (MQW) structure are measured to identify the cause of low efficiencies in high In-content InGaN quantum w…

Demand Shaping Through Bundling and Product Configuration : A Dynamic Multipr…

In today’s digital age, with the aid of the internet and data mining, many firms use vertically differentiated product bundling to influence demand to match up with inventory status, especially i…

Learning Regional Attraction for Line Segment Detection

This paper presents regional attraction of line segment maps, and hereby poses the problem of line segment detection (LSD) as a problem of region coloring. Given a line segment map, the proposed re…

Fast and Unsupervised Neural Architecture Evolution for Visual Representation…

Unsupervised visual representation learning is one of the hottest topics in computer vision, yet performance still lags behind compared with the best supervised learning methods. At the same time, …

A Functional Representation for Graph Matching

Cyber-Physical Systems for Water Sustainability : Challenges and Opportunities