Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.

A non-photorealistic rendering technique is presented for generating images such as stippling images and paper mosaic images with various shapes of paper pieces. Paper pieces are spatially arranged by using an anisotropic Lp poisson disk sampling. The shape of paper pieces is adaptively varied by changing the value of p. We demonstrate with experiments that edges and details in an input image are preserved by the pieces according to the anisotropy of their shape.

Aiming at the problem of spatial focus regions distribution dispersion and dislocation in feature pyramid networks and insufficient feature dependency acquisition in both spatial and channel dimensions, this paper proposes a spatial-temporal aggregated shuffle attention for video instance segmentation (STASA-VIS). First, an mixed subsampling (MS) module to embed activating features from the low-level target area of feature pyramid into the high-level is designed, so as to aggregate spatial information on target area. Taking advantage of the coherent information in video frames, STASA-VIS uses the first ones of every 5 video frames as the key-frames and then propagates the keyframe feature maps of the pyramid layers forward in the time domain, and fuses with the non-keyframe mixed subsampled features to achieve time-domain consistent feature aggregation. Finally, STASA-VIS embeds shuffle attention in the backbone to capture the pixel-level pairwise relationship and dimensional dependencies among the channels and reduce the computation. Experimental results show that the segmentation accuracy of STASA-VIS reaches 41.2%, and the test speed reaches 34FPS, which is better than the state-of-the-art one stage video instance segmentation (VIS) methods in accuracy and achieves real-time segmentation.

This paper presents a novel method for weakly supervised semantic segmentation of 3D point clouds using a novel graph and edge convolutional neural network (GECNN) towards 1% and 10% point cloud with labels. Our general framework facilitates semantic segmentation by encoding both global and local scale features via a parallel graph and edge aggregation scheme. More specifically, global scale graph structure cues of point clouds are captured by a graph convolutional neural network, which is propagated from pairwise affinity representation over the whole graph established in a d-dimensional feature embedding space. We integrate local scale features derived from a dynamic edge feature aggregation convolutional neural networks that allows us to fusion both global and local cues of 3D point clouds. The proposed GECNN model is trained by using a comprehensive objective which consists of incomplete, inexact, self-supervision and smoothness constraints based on partially labeled points. The proposed approach enforces global and local consistency constraints directly on the objective losses. It inherently handles the challenges of segmenting sparse 3D point clouds with limited annotations in a large scale point cloud space. Our experiments on the ShapeNet and S3DIS benchmarks demonstrate the effectiveness of the proposed approach for efficient (within 20 epochs) learning of large scale point cloud semantics despite very limited labels.

We propose a method for downsizing line pictures to generate pixel line arts. In our method, topological properties such as connectivity of lines and segments are preserved by allowing slight distortion in the form of objects in input images. When input line pictures are painted with colors, the number of colors is preserved by our method.

In this paper we propose a new blind adaptive compensator associated with the inverse QRD-RLS (IQRD-RLS) algorithm to adaptively estimate the parameters, related to the effects of gain/phase imbalance and DC offsets occur in the Quadrature demodulator, for compensation. In this new approach the power measurement of the received signal is employed to develop the blind adaptation algorithm for compensator, it does not require any reference signal transmitted from the transmitter and possess the fast convergence rate and better numerical stability. To verify the great improvement, in terms of reducing the effects of the imbalance and offset, over existing techniques computer simulation is carried out for the coherent 16 PSK-communication system. We show that the proposed blind scheme has rapidly convergence rate and the smaller mean square error in steady state.

Along with the proliferation of IoT (Internet of Things) devices, cyberattacks towards them are on the rise. In this paper, aiming at efficient precaution and mitigation of emerging IoT cyberthreats, we present a multimodal study on applying machine learning methods to characterize malicious programs which target multiple IoT platforms. Experiments show that opcode sequences obtained from static analysis and API sequences obtained by dynamic analysis provide sufficient discriminant information such that IoT malware can be classified with near optimal accuracy. Automated and accelerated identification and mitigation of new IoT cyberthreats can be enabled based on the findings reported in this study.

Real-time on-chip measurement of bit error rate (BER) for high-speed analog-to-digital converters (ADCs) does not only require expensive multi-port high-speed data acquisition equipment but also enormous post-processing. This paper proposes a low-cost built-in-self-test (BIST) circuit for high-speed ADC BER test. Conventionally, the calculation of BER requires a high-speed adder. The presented method takes the advantages of Gray coding and only needs simple logic circuits for BER evaluation. The prototype of the BIST circuit is fabricated along with a 5-bit high-speed flash ADC in a 90-nm CMOS process. The active area is only 90 µm 70 µm and the average power consumption is around 0.3 mW at 700 MS/s. The measurement of the BIST circuit shows consistent results with the measurement by external data acquisition equipment.

This paper considers a massive multiple-input-multiple-output (MIMO) relaying system with multi-pair single-antenna users. The relay node adopts maximum-ratio combining/maximum-ratio transmission (MRC/MRT) stratagem for reception/transmission. We analyze the spectral efficiency (SE) and power scaling laws with respect to the number of relay antennas and other system parameters. First, by using the law of large numbers, we derive the closed-form expression of the SE, based on which, it is shown that the SE per user increases with the number of relay antennas but decreases with the number of user pairs, both logarithmically. It is further discovered that the transmit power at the source users and the relay can be continuously reduced as the number of relay antennas becomes large while the SE can maintains a constant value, which also means that the energy efficiency gain can be obtained simultaneously. Moreover, it is proved that the number of served user pairs can grow proportionally over the number of relay antennas with arbitrary SE requirement and no extra power cost. All the analytical results are verified through the numerical simulations.

A drastic increase in cyberattacks targeting Internet of Things (IoT) devices using telnet protocols has been observed. IoT malware continues to evolve, and the diversity of OS and environments increases the difficulty of executing malware samples in an observation setting. To address this problem, we sought to develop an alternative means of investigation by using the telnet logs of IoT honeypots and analyzing malware without executing it. In this paper, we present a malware classification method based on malware binaries, command sequences, and meta-features. We employ both unsupervised or supervised learning algorithms and text-mining algorithms for handling unstructured data. Clustering analysis is applied for finding malware family members and revealing their inherent features for better explanation. First, the malware binaries are grouped using similarity analysis. Then, we extract key patterns of interaction behavior using an N-gram model. We also train a multiclass classifier to identify IoT malware categories based on common infection behavior. For misclassified subclasses, second-stage sub-training is performed using a file meta-feature. Our results demonstrate 96.70% accuracy, with high precision and recall. The clustering results reveal variant attack vectors and one denial of service (DoS) attack that used pure Linux commands.