Siamese visual tracking, viewed as a problem of max-similarity matching to the target template, has absorbed increasing attention in computer vision. However, it is a challenge for current Siamese trackers that the demands of balance between accuracy in real-time tracking and robustness in long-time tracking are hard to meet. This work proposes a new Siamese based tracker with a dual-pipeline correlated fusion network (named as ADF-SiamRPN), which consists of one initial template for robust correlation, and the other transient template with the ability of adaptive feature optimal selection for accurate correlation. By the promotion from the learnable correlation-response fusion network afterwards, we are in pursuit of the synthetical improvement of tracking performance. To compare the performance of ADF-SiamRPN with state-of-the-art trackers, we conduct lots of experiments on benchmarks like OTB100, UAV123, VOT2016, VOT2018, GOT-10k, LaSOT and TrackingNet. The experimental results of tracking demonstrate that ADF-SiamRPN outperforms all the compared trackers and achieves the best balance between accuracy and robustness.

Binary neural networks (BNNs), where both activations and weights are radically quantized to be {-1, +1}, can massively accelerate the run-time performance of convolution neural networks (CNNs) for edge devices, by computation complexity reduction and memory footprint saving. However, the non-differentiable binarizing function used in BNNs, makes the binarized models hard to be optimized, and introduces significant performance degradation than the full-precision models. Many previous works managed to correct the backward gradient of binarizing function with various improved versions of straight-through estimation (STE), or in a gradual approximate approach, but the gradient suppression problem was not analyzed and handled. Thus, we propose a novel gradient corrected approximation (GCA) method to match the discrepancy between binarizing function and backward gradient in a gradual and stable way. Our work has two primary contributions: The first is to approximate the backward gradient of binarizing function using a simple leaky-steep function with variable window size. The second is to correct the gradient approximation by standardizing the backward gradient propagated through binarizing function. Experiment results show that the proposed method outperforms the baseline by 1.5% Top-1 accuracy on ImageNet dataset without introducing extra computation cost.

When a failure occurs in a network element, such as switch, router, and server, network operators need to recognize the service impact, such as time to recovery from the failure or severity of the failure, since service impact is essential information for handling failures. In this paper, we propose Deep learning based Service Impact Prediction system (DeepSIP), which predicts the service impact of network failure in a network element using a temporal multimodal convolutional neural network (CNN). More precisely, DeepSIP predicts the time to recovery from the failure and the loss of traffic volume due to the failure in a network on the basis of information from syslog messages and traffic volume. Since the time to recovery is useful information for a service level agreement (SLA) and the loss of traffic volume is directly related to the severity of the failure, we regard the time to recovery and the loss of traffic volume as the service impact. The service impact is challenging to predict, since it depends on types of network failures and traffic volume when the failure occurs. Moreover, network elements do not explicitly contain any information about the service impact. To extract the type of network failures and predict the service impact, we use syslog messages and past traffic volume. However, syslog messages and traffic volume are also challenging to analyze because these data are multimodal, are strongly correlated, and have temporal dependencies. To extract useful features for prediction, we develop a temporal multimodal CNN. We experimentally evaluated DeepSIP in terms of accuracy by comparing it with other NN-based methods by using synthetic and real datasets. For both datasets, the results show that DeepSIP outperformed the baselines.

This paper proposes a measurement-based spectrum database (MSD) with clustered fading distributions toward greater storage efficiencies. The conventional MSD can accurately model the actual characteristics of multipath fading by plotting the histogram of instantaneous measurement data for each space-separated mesh and utilizing it in communication designs. However, if the database contains all of a distribution for each location, the amount of data stored will be extremely large. Because the main purpose of the MSD is to improve spectral efficiency, it is necessary to reduce the amount of data stored while maintaining quality. The proposed method reduces the amount of stored data by estimating the distribution of the instantaneous received signal power at each point and integrating similar distributions through clustering. Numerical results show that clustering techniques can reduce the amount of data while maintaining the accuracy of the MSD. We then apply the proposed method to the outage probability prediction for the instantaneous received signal power. It is revealed that the prediction accuracy is maintained even when the amount of data is reduced.

The phenomenon where a speaker mixes two or more languages within the same conversation is called code-switching (CS). Handling CS is challenging for automatic speech recognition (ASR) and text-to-speech (TTS) because it requires coping with multilingual input. Although CS text or speech may be found in social media, the datasets of CS speech and corresponding CS transcriptions are hard to obtain even though they are required for supervised training. This work adopts a deep learning-based machine speech chain to train CS ASR and CS TTS with each other with semisupervised learning. After supervised learning with monolingual data, the machine speech chain is then carried out with unsupervised learning of either the CS text or speech. The results show that the machine speech chain trains ASR and TTS together and improves performance without requiring the pair of CS speech and corresponding CS text. We also integrate language embedding and language identification into the CS machine speech chain in order to handle CS better by giving language information. We demonstrate that our proposed approach can improve the performance on both a single CS language pair and multiple CS language pairs, including the unknown CS excluded from training data.

Video-based person re-identification (re-ID) aims at retrieving person across non-overlapping camera and has achieved promising results owing to deep convolutional neural network. Due to the dynamic properties of the video, the problems of background clutters and occlusion are more serious than image-based person Re-ID. In this letter, we present a novel triple attention network (TriANet) that simultaneously utilizes temporal, spatial, and channel context information by employing the self-attention mechanism to get robust and discriminative feature. Specifically, the network has two parts, where the first part introduces a residual attention subnetwork, which contains channel attention module to capture cross-dimension dependencies by using rotation and transformation and spatial attention module to focus on pedestrian feature. In the second part, a time attention module is designed to judge the quality score of each pedestrian, and to reduce the weight of the incomplete pedestrian image to alleviate the occlusion problem. We evaluate our proposed architecture on three datasets, iLIDS-VID, PRID2011 and MARS. Extensive comparative experimental results show that our proposed method achieves state-of-the-art results.

We propose a useful formulation for ill-posed inverse problems in Hilbert spaces with nonlinear clipping effects. Ill-posed inverse problems are often formulated as optimization problems, and nonlinear clipping effects may cause nonconvexity or nondifferentiability of the objective functions in the case of commonly used regularized least squares. To overcome these difficulties, we present a tractable formulation in which the objective function is convex and differentiable with respect to optimization variables, on the basis of the Bregman divergence associated with the primitive function of the clipping function. By using this formulation in combination with the representer theorem, we need only to deal with a finite-dimensional, convex, and differentiable optimization problem, which can be solved by well-established algorithms. We also show two practical examples of inverse problems where our theory can be applied, estimation of band-limited signals and time-harmonic acoustic fields, and evaluate the validity of our theory by numerical simulations.

In this letter, we will prove that chaotic binary sequences generated by the tent map and Walsh functions are i.i.d. (independent and identically distributed) and orthogonal to each other.

In sixth-generation (6G) mobile communication system, it is expected that extreme high data rate communication with a peak data rate over 100Gbps should be provided by exploiting higher frequency bands in addition to millimeter-wave bands such as 28GHz. The higher frequency bands are assumed to be millimeter wave and terahertz wave where the extreme wider bandwidth is available compared with 5G, and hence 6G needs to promote research and development to exploit so-called terahertz wave targeting the frequency from 100GHz to 300GHz. In the terahertz wave, there are fundamental issues that rectilinearity and pathloss are higher than those in the 28GHz band. In order to solve these issues, it is very important to clarify channel characteristics of the terahertz wave and establish a channel model, to advance 6G radio access technologies suitable for the terahertz wave based on the channel model, and to develop radio-frequency device technologies for such higher frequency bands. This paper introduces a direction of studies on 6G radio access technologies to explore the higher frequency bands and technical issues on the device technologies, and then basic computer simulations in 100Gbps transmission using 100GHz band clarify a potential of extreme high data rate over 100Gbps.

This letter expands the previously proposed High Time Resolution Carrier Interferometry (HTRCI) to estimate a larger amount of channel status information (CSI). HTRCI is based on a comb-type pilot symbol on OFDM and CSI for null subcarriers are interpolated by time-domain signal processing. In order to utilize such null pilot subcarriers for increasing estimable CSI, they should generally be separated in frequency-domain prior to estimation and interpolation processes. The main proposal is its separation scheme in conjunction with the HTRCI treatment of the temporal domain. Its effectiveness is verified by a pilot de-contamination on downlink two-cell MIMO transmission scenario. Binary error rate (BER) performance can be improved in comparison to conventional HTRCI and zero padding (ZP) which replaces the impulse response alias with zeros.

This paper proposes a physical-layer cell identity (PCID) detection method that uses joint estimation of the frequency offset and secondary synchronization signal (SSS) sequence for the 5G new radio (NR) initial access with beamforming transmission at a base station. Computer simulation results show that using the PCID detection method with the proposed joint estimation yields an almost identical PCID detection probability as the primary synchronization signal (PSS) detection probability at an average received signal-to-noise ratio (SNR) of higher than approximately -5dB suggesting that the residual frequency offset is compensated to a sufficiently low level for the SSS sequence estimation. It is also shown that the PCID detection method achieves a high PCID detection probability of greater than 90% and 50% at the carrier frequency of 30 and 50GHz, respectively, at the average received SNR of 0dB for the frequency stability of a user equipment oscillator of 3ppm.

Iterative block decision feedback equalization with hard-decision feedback (HD-IBDFE) was proposed for single-carrier transmission with frequency-domain equalization (SC-FDE). The detection performance hinges upon not only error propagation, but also the accuracy of estimating the parameters used to re-compute the equalizer coefficients at each iteration. In this paper, we use the erasure zone (EZ) to de-emphasize the feedback values when the hard decisions are not reliable. EZ use also enables a more accurate, and yet computationally more efficient, parameter estimation method than HD-IBDFE. We show that the resulting equalizer coefficients share the same mathematical form as that of the HD-IBDFE, thereby preserving the merit of not requiring matrix inverse operations in calculating the equalizer coefficients. Simulations show that, by using the EZ and the proposed parameter estimation method, a significant performance improvement over the conventional HD-IBDFE can be achieved, but with lower complexity.

The Tokyo subway is one of the most complex subway networks in the world and it is difficult to compute a visually readable metro map using existing layout methods. In this paper, we present a new method that can generate complex metro maps such as the Tokyo subway network. Our method consists of two phases. The first phase generates rough metro maps. It decomposes the metro networks into smaller subgraphs and partially generates rough metro maps. In the second phase, we use a local search technique to improve the aesthetic quality of the rough metro maps. The experimental results including the Tokyo metro map are shown.

Well annotated dataset is crucial to the training of object detectors. However, the production of finely annotated datasets for object detection tasks is extremely labor-intensive, therefore, cloud sourcing is often used to create datasets, which leads to these datasets tending to contain incorrect annotations such as inaccurate localization bounding boxes. In this study, we highlight a problem of object detection with noisy bounding box annotations and show that these noisy annotations are harmful to the performance of deep neural networks. To solve this problem, we further propose a framework to allow the network to modify the noisy datasets by alternating refinement. The experimental results demonstrate that our proposed framework can significantly alleviate the influences of noise on model performance.

Most aggregate signature schemes are relying on pairings, but high computational and storage costs of pairings limit the feasibility of those schemes in practice. Zhao proposed the first pairing-free aggregate signature scheme (AsiaCCS 2019). However, the security of Zhao's scheme is based on the hardness of a newly introduced non-standard computational problem. The recent impossibility results of Drijvers et al. (IEEE S&P 2019) on two-round pairing-free multi-signature schemes whose security based on the standard discrete logarithm (DL) problem have strengthened the view that constructing a pairing-free aggregate signature scheme which is proven secure based on standard problems such as DL problem is indeed a challenging open problem. In this paper, we offer a novel solution to this open problem. We introduce a new paradigm of aggregate signatures, i.e., aggregate signatures with an additional pre-communication stage. In the pre-communication stage, each signer interacts with the aggregator to agree on a specific random value before deciding messages to be signed. We also discover that the impossibility results of Drijvers et al. take effect if the adversary can decide the whole randomness part of any individual signature. Based on the new paradigm and our discovery of the applicability of the impossibility result, we propose a pairing-free aggregate signature scheme such that any individual signature includes a random nonce which can be freely generated by the signer. We prove the security of our scheme based on the hardness of the standard DL problem. As a trade-off, in contrast to the plain public-key model, which Zhao's scheme uses, we employ a more restricted key setup model, i.e., the knowledge of secret-key model.

We developed a Nb 4-layer process for fabricating superconducting integrated circuits that involves using caldera planarization to increase the flexibility and reliability of the fabrication process. We call this process the planarized high-speed standard process (PHSTP). Planarization enables us to flexibly adjust most of the Nb and SiO2 film thicknesses; we can select reduced film thicknesses to obtain larger mutual coupling depending on the application. It also reduces the risk of intra-layer shorts due to etching residues at the step-edge regions. We describe the detailed process flows of the planarization for the Josephson junction layer and the evaluation of devices fabricated with PHSTP. The results indicated no short defects or degradation in junction characteristics and good agreement between designed and measured inductances and resistances. We also developed single-flux-quantum (SFQ) and adiabatic quantum-flux-parametron (AQFP) logic cell libraries and tested circuits fabricated with PHSTP. We found that the designed circuits operated correctly. The SFQ shift-registers fabricated using PHSTP showed a high yield. Numerical simulation results indicate that the AQFP gates with increased mutual coupling by the planarized layer structure increase the maximum interconnect length between gates.

In the bin packing problem, we are asked to place given items, each being of size between zero and one, into bins of capacity one. The goal is to minimize the number of bins that contain at least one item. An online algorithm for the bin packing problem decides where to place each item one by one when it arrives. The asymptotic approximation ratio of the bin packing problem is defined as the performance of an optimal online algorithm for the problem. That value indicates the intrinsic hardness of the bin packing problem. In this paper we study the bin packing problem in which every item is of either size α or size β (≤ α). While the asymptotic approximation ratio for $alpha > rac{1}{2}$ was already identified, that for $alpha leq rac{1}{2}$ is only partially known. This paper is the first to give a lower bound on the asymptotic approximation ratio for any $alpha leq rac{1}{2}$, by formulating linear optimization problems. Furthermore, we derive another lower bound in a closed form by constructing dual feasible solutions.

In this paper, we address the problem of detector design in severely frequency-selective channels for spatial multiplexing systems that adopt filter bank multicarrier based on offset quadrature amplitude modulation (FBMC/OQAM) as the communication waveforms. We consider decision feedback equalizers (DFEs) that use multiple feedback filters to jointly cancel the post-cursor components of inter-symbol interference, inter-antenna interference, and, in some configuration, inter-subchannel interference. By exploiting the special structures of the correlation matrix and the staggered property of the FBMC/OQAM signals, we obtain an efficient method of computing the DFE coefficients that requires a smaller number of multiplications than the linear equalizer (LE) and conventional DFE do. The simulation results show that the proposed detectors considerably outperform the LE and conventional DFE at moderate-to-high signal-to-noise ratios.

Computing the weight distribution of a code is a challenging problem in coding theory. In this paper, the weight distributions of (256, k) extended binary primitive BCH codes with k≤71 and k≥187 are given. The weight distributions of the codes with k≤63 and k≥207 have already been obtained in our previous work. Affine permutation and trellis structure are used to reduce the computing time. Computer programs in C language which use recent CPU instructions, such as SIMD, are developed. These programs can be deployed even on an entry model workstation to obtain the new results in this paper.

This paper presents an efficient method for solving PnP, PnPf, and PnPfr problems, which are the problems of determining camera parameters from 2D-3D point correspondences. The proposed method is derived based on a simple usage of linear algebra, similarly to the classical DLT methods. Therefore, the new method is easier to understand, easier to implement, and several times faster than the state-of-the-art methods using Gröbner basis. Contrary to the existing Gröbner basis methods, the proposed method consists of three algorithms depending on the number of the points and the 3D point configuration. Experimental results show that the proposed method is as accurate as the state-of-the-art methods even in near-planar scenes while achieving up to three times faster.