Search

Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific discriminative features and fine-grained correlation features for TIR tracking. Specifically, we first use an auxiliary classification network to guide the generation of TIR-specific discriminative features for distinguishing the TIR objects belonging to different classes. Second, we design a fine-grained aware module to capture more subtle information for distinguishing the TIR objects belonging to the same class. These two kinds of features complement each other and recognize TIR objects in the levels of inter-class and intra-class respectively. These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task. In addition, we develop a large-scale TIR training dataset to train the network for adapting the model to the TIR domain. Extensive experimental results on three benchmarks show that the proposed algorithm achieves a relative gain of 10% over the baseline and performs favorably against the state-of-the-art methods. Codes and the proposed TIR dataset are available at {https://github.com/QiaoLiuHit/MMNet}., Comment: Thirty-Fourth AAAI Conference on Artifical Intelligence

In this paper, we study the problem of optimal scheduling of content placement along time in a base station with limited cache capacity, taking into account jointly the offloading effect and freshness of information. We model offloading based on popularity in terms of the number of requests and information freshness based on the notion of age of information (AoI). The objective is to reduce the load of backhaul links as well as the AoI of contents in the cache via a joint cost function. For the resulting optimization problem, we prove its hardness via a reduction from the Partition problem. Next, via a mathematical reformulation, we derive a solution approach based on column generation and a tailored rounding mechanism. Finally, we provide performance evaluation results showing that our algorithm provides near-optimal solutions.

In this technical note, we present a new theoretical result for resource optimization with non-orthogonal multiple access (NOMA). For multi-cell scenarios, a so-called load-coupling model has been proposed to characterize the presence of mutual interference for NOMA, and resource optimization relies on the use of fixed-point iterations [1], [2] across cells. One difficulty here is that the order of decoding for successive interference cancellation (SIC) in NOMA is generally not known a priori. This is because the decoding order in one cell depends on interference, which, in turn, is governed by resource allocation in other cells, and vice versa. To achieve convergence, previous works have used workarounds that pose restrictions to NOMA, such that the SIC decoding order remains in optimization. As a comment to [1], [2], we derive and prove the following result: The convergence is guaranteed, even if the order changes over the iterations. The result not only waives the need of previous workarounds, but also implies that a wide class of resource optimization problems for multi-cell NOMA is tractable, as long as that for single cell is.

Existing deep Thermal InfraRed (TIR) trackers only use semantic features to describe the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images.To address this issue, we propose a multi-level similarity model under a Siamese framework for robust TIR object tracking. Specifically, we compute different pattern similarities on two convolutional layers using the proposed multi-level similarity network. One of them focuses on the global semantic similarity and the other computes the local structural similarity of the TIR object. These two similarities complement each other and hence enhance the discriminative capacity of the network for handling distractors. In addition, we design a simple while effective relative entropy based ensemble subnetwork to integrate the semantic and structural similarities. This subnetwork can adaptive learn the weights of the semantic and structural similarities at the training stage. To further enhance the discriminative capacity of the tracker, we construct the first large scale TIR video sequence dataset for training the proposed model. The proposed TIR dataset not only benefits the training for TIR tracking but also can be applied to numerous TIR vision tasks. Extensive experimental results on the VOT-TIR2015 and VOT-TIR2017 benchmarks demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods., Comment: 18 pages

Joint scheduling and routing of data flows with deadline constraints in communication networks has been attracting research interest. This type of problem distinguishes from conventional multicommodity flows due to the presence of the time dimension. In this paper, we address a flow routing and scheduling problem with delivery deadline, where the assignment of link capacity occurs in discrete units. Discrete capacity allocation is motivated by applications in communication systems, where it is common to have a base unit of capacity (e.g., wavelength channel in optical communications). We present and prove complexity results of the problem. Next, we give an optimization formulation based on a time slicing approach (TSA), which amounts to a discretization of the time into time slices to enable to formulate the deadline constraints. We then derive an effective reformulation of the problem, via which a column generation algorithm (CGA) is developed. In addition, we propose a simple and fast Max-Flow based Algorithm (MFA). We use a number of network and traffic scenarios to study various performance aspects of the algorithms.

This paper investigates how to mitigate the impact of adjacent channel interference (ACI) in vehicular broadcast communication, using scheduling and power control. Our objective is to maximize the number of connected vehicles. First, we formulate the joint scheduling and power control problem as a mixed Boolean linear programming (MBLP) problem. From this problem formulation, we derive scheduling alone problem as Boolean linear programming (BLP) problem, and power control alone problem as an MBLP problem. Due to the hardness in solving joint scheduling and power control for multiple timeslots, we propose a column generation method to reduce the computational complexity. We also observe that the problem is highly numerically sensitive due to the high dynamic range of channel parameters and adjacent channel interference ratio (ACIR) values. Therefore, we propose a novel sensitivity reduction technique, which can compute the optimal solution. Finally, we compare the results for optimal scheduling, near-optimal joint scheduling and power control schemes, and conclude that the effective scheduling and power control schemes indeed significantly improve the performance.

Caching popular contents at edge devices is an effective solution to alleviate the burden of the backhaul networks. Earlier investigations commonly neglected the storage cost in caching. More recently, retention-aware caching, where both the downloading cost and storage cost are accounted for, is attracting attention. Motivated by this, we address proactive and retention-aware caching with user mobility, optimizing the sum of the two types of costs. This is a combinatorial optimization problem. However, we derive a stream of analytical results and they together lead to an algorithm that guarantees global optimum with polynomial-time complexity. Numerical results show significant improvements in comparison to popular caching and random caching., Comment: submitted to the 2018 IEEE 88th Vehicular Technology Conference

Task offloading is a key component in mobile edge computing. Offloading a task to a remote server takes communication and networking resources. An alternative is device-todevice (D2D) offloading, where a task of a device is offloaded to some device having computational resource available. The latter requires that the devices are within the range of each other, first for task collection, and later for result gathering. Hence, in mobility scenarios, the performance of D2D offloading will suffer if the contact rates between the devices are low. We enhance the setup to base station (BS) assisted D2D offloading, namely, a BS can act as a relay for task distribution or result collection. However, this would imply additional consumption of wireless resource. The associated cost and the improvement in completion time of task offloading compose a fundamental trade-off. For the resulting optimization problem, we mathematically prove the complexity, and propose an algorithm using Lagrangian duality. The simulation results demonstrate not only that the algorithm has close-to-optimal performance, but also provide structural insights of the optimal trade-off., Comment: accepted in the 2019 IEEE 89th Vehicular Technology Conference

Relaying techniques for millimeter-wave wireless networks represent a powerful solution for improving the transmission performance. In this work, we quantify the benefits in terms of delay and throughput for a random-access multi-user millimeter-wave wireless network, assisted by a full-duplex network cooperative relay. The relay is equipped with a queue for which we analyze the performance characteristics (e.g., arrival rate, service rate, average size, and stability condition). Moreover, we study two possible transmission schemes: fully directional and broadcast. In the former, the source nodes transmit a packet either to the relay or to the destination by using narrow beams, whereas, in the latter, the nodes transmit to both the destination and the relay in the same timeslot by using a wider beam, but with lower beamforming gain. In our analysis, we also take into account the beam alignment phase that occurs every time a transmitter node changes the destination node. We show how the beam alignment duration, as well as position and number of transmitting nodes, significantly affect the network performance. Moreover, we illustrate the optimal transmission scheme (i.e., broadcast or fully directional) for several system parameters and show that a fully directional transmission is not always beneficial, but, in some scenarios, broadcasting and relaying can improve the performance in terms of throughput and delay., Comment: arXiv admin note: text overlap with arXiv:1804.09450

Long Term Evolution (LTE)-Wireless Local Area Network (WLAN) Path Aggregation (LWPA) based on Multi-path Transmission Control Protocol (MPTCP) has been under standardization procedure as a promising and cost-efficient solution to boost Downlink (DL) data rate and handle the rapidly increasing data traffic. This paper aims at providing tractable analysis for the DL performance evaluation of large-scale LWPA networks with the help of tools from stochastic geometry. We consider a simple yet practical model to determine under which conditions a native WLAN Access Point (AP) will work under LWPA mode to help increasing the received data rate. Using stochastic spatial models for the distribution of WLAN APs and LTE Base Stations (BSs), we analyze the density of active LWPA-mode WiFi APs in the considered network model, which further leads to closed-form expressions on the DL data rate and area spectral efficiency (ASE) improvement. Our numerical results illustrate the impact of different network parameters on the performance of LWPA networks, which can be useful for further performance optimization., Comment: IEEE GLOBECOM 2017

Multi-connectivity is emerging as promising solution to provide reliable communications and seamless connectivity at the millimeter-wave frequency range. Due to the obstacles that cause frequent interruptions at such high frequency range, connectivity to multiple cells can drastically increase the network performance in terms of throughput and reliability by coordination among the network elements. In this paper, we propose an algorithm for the link scheduling optimization that maximizes the network throughput for multi-connectivity in millimeter-wave cellular networks. The considered approach exploits a centralized architecture, fast link switching, proactive context preparation and data forwarding between millimeter-wave access points and the users. The proposed algorithm is able to numerically approach the global optimum and to quantify the potential gain of multi-connectivity in millimeter-wave cellular networks.

In this work, we analyze the throughput of random access multi-user relay-assisted millimeter-wave wireless networks, in which both the destination and the relay have multipacket reception capability. We consider a full-duplex network cooperative relay that stores the successfully received packets in a queue, for which we analyze the performance. Moreover, we study the effects on the network throughput of two different strategies, by which the source nodes transmit either a packet to both the destination and the relay in the same timeslot by using wider beams (broadcast approach) or to only one of these two by using narrower beams (fully directional approach). We consider the inter-beam interference at the receiver and show the optimal strategy with respect to several system parameters, e.g., positions and number of the nodes.

A delay-optimal caching problem (DOCP) in deviceto- device (D2D) networks with moblity is modelled. The problem arises in the context of achieving offloading using device caching, and the offloading effect is represented by the expected network load ratio (NLR) which is the percentage of data that has to be downloaded from the network. Compared with the related studies, this work considers minimizing delay with NLR guarantee in mobility scenarios. A lower bound of global optimum is derived, thus enabling performance benchmarking of any sub-optimal algorithm. For problem-solving, an effective search algorithm (ESA) is proposed based on the bound. Simulations are conducted to evaluate the effectiveness of the ESA algorithm., Comment: To appear in IEEE Wireless Communication Letters

We explore the potential of optimizing resource allocation with flexible numerology in frequency domain and variable frame structure in time domain, in presence of services with different types of requirements. We analyze the computational complexity and propose a scalable optimization algorithm based on searching in both the primal space and dual space that are complementary to each other. Numerical results show significant advantages of adopting flexibility in both time and frequency domains for capacity enhancement and meeting the requirements of mission critical services., Comment: 4 pages

Non-orthogonal multiple access (NOMA) allows multiple users to simultaneously access the same time-frequency resource by using superposition coding and successive interference cancellation (SIC). Thus far, most papers on NOMA have focused on performance gain for one or sometimes two base stations. In this paper, we study multi-cell NOMA and provide a general framework for user clustering and power allocation, taking into account inter-cell interference, for optimizing resource allocation of NOMA in multi-cell networks of arbitrary topology. We provide a series of theoretical analysis, to algorithmically enable optimization approaches. The resulting algorithmic notion is very general. Namely, we prove that for any performance metric that monotonically increases in the cells' resource consumption, we have convergence guarantee for global optimum. We apply the framework with its algorithmic concept to a multi-cell scenario to demonstrate the gain of NOMA in achieving significantly higher efficiency., Comment: 7 pages