Most of existing correlation filter-based tracking approaches only estimate simple axis-aligned bounding boxes, and very few of them is capable of recovering the underlying similarity transformation. To a large extent, such limitation restricts the applications of such trackers for a wide range of scenarios. In this paper, we propose a novel correlation filter-based tracker with robust estimation of similarity transformation on the large displacements to tackle this challenging problem. In order to efficiently search in such a large 4-DoF space in real-time, we formulate the problem into two 2-DoF sub-problems and apply an efficient Block Coordinates Descent solver to optimize the estimation result. Specifically, we employ an efficient phase correlation scheme to deal with both scale and rotation changes simultaneously in log-polar coordinates. Moreover, a fast variant of correlation filter is used to predict the translational motion individually. Our experimental results demonstrate that the proposed tracker achieves very promising prediction performance compared with the state-of-the-art visual object tracking methods while still retaining the advantages of efficiency and simplicity in conventional correlation filter-based tracking methods.
The difference result of domain name translating between multi DNS servers makes a big discrepancy of routing and timelag when data packet goes into the Internet.This paper gives a routing and forwarding method based on domain name judgment to resolve this problem.In order to obtain the analytical result of the optimal access path and minimum timelag,as well as improve the network quality and service quality.
Deep Neural Networks (DNN) could forget the knowledge about earlier tasks when learning new tasks, which is known as catastrophic forgetting. To learn new task without forgetting, recently, the mask-based learning method (e.g. piggyback [10]) is proposed to address this issue by learning only a binary element-wise mask, while keeping the backbone model fixed. However, the binary mask has limited modeling capacity for new tasks. A more recent work [5] proposes a compress-grow-based method (CPG) to achieve better accuracy for new tasks by partially training backbone model, but with order-higher training cost, which makes it infeasible to be deployed into popular state-of-the-art edge-/mobile-learning. The primary goal of this work is to simultaneously achieve fast and high-accuracy multi task adaption in continual learning setting. Thus motivated, we propose a new training method called Kernelwise Soft Mask (KSM), which learns a kernel-wise hybrid binary and real-value soft mask for each task. Such a hybrid mask can be viewed as a superposition of a binary mask and a properly scaled real-value tensor, which offers a richer representation capability without low-level kernel support to meet the objective of low hardware overhead. We validate KSM on multiple benchmark datasets against recent state-of-the-art methods (e.g. Piggyback, Packnet, CPG, etc.), which shows good improvement in both accuracy and training cost.
In this paper, an overview of novel design and integration approaches for improved performance UHF Radio Frequency Identification (RFID) tags with embedded power source and sensing capability is presented. Ultra-low-cost organic substrates, such as paper, with inkjet-printing capability are investigated for the UHF frequency band. The proposed technology could potentially revolutionize sensor nodes and RFII) tags for various applications such as security, logistics, automotive and pharmaceutical.
The research on event detection in unmanned aerial videos has received a large attention in the recent years. Plenty of methods have been proposed in this area. However, there is no agreement on which methods fit well for the application in the unmanned aerial videos and which methods fit well for certain event detection. In this paper, we present a framework for event detection in unmanned aerial videos and proposed a series of events to be detected. We mainly divide these events into two categories according to whether the event subject can be well detected and tracked, and all of them are rule-based and model-based. The framework we proposed will adapt to the event detection task. In rule-based event detection, we will give some design methods by way of examples. And in model-based event detection, we will introduce some popular methods in this area and will give out evaluation methods.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)