Negation scope resolution is the process of detecting the negated part of a sentence. Unlike the syntax-based approach employed in previous researches, state-of-the-art methods performed better without the explicit use of syntactic structure. This work revisits the syntax-based approach and re-evaluates the effectiveness of syntactic structure in negation scope resolution. We replace the parser utilized in the prior works with state-of-the-art parsers and modify the syntax-based heuristic rules. The experimental results demonstrate that the simple modifications enhance the performance of the prior syntax-based method to the same level as state-of-the-art end-to-end neural-based methods.

Most existing multi-view subspace clustering approaches only capture the inter-view similarities between different views and ignore the optimal local geometric structure of the original data. To this end, in this letter, we put forward a novel method named shared latent embedding learning for multi-view subspace clustering (SLE-MSC), which can efficiently capture a better latent space. To be specific, we introduce a pseudo-label constraint to capture the intra-view similarities within each view. Meanwhile, we utilize a novel optimal graph Laplacian to learn the consistent latent representation, in which the common manifold is considered as the optimal manifold to obtain a more reasonable local geometric structure. Comprehensive experimental results indicate the superiority and effectiveness of the proposed method.

We propose a novel classification problem setting where Undesirable Classes (UCs) are defined for each class. UC is the class you specifically want to avoid misclassifying. To address this setting, we propose a framework to reduce the probabilities for UCs while increasing the probability for a correct class.

In practice, even a well-trained neural machine translation (NMT) model can still make biased inferences on the training set due to distribution shifts. For the human learning process, if we can not reproduce something correctly after learning it multiple times, we consider it to be more difficult. Likewise, a training example causing a large discrepancy between inference and reference implies higher learning difficulty for the MT model. Therefore, we propose to adopt the inference discrepancy of each training example as the difficulty criterion, and according to which rank training examples from easy to hard. In this way, a trained model can guide the curriculum learning process of an initial model identical to itself. We put forward an analogy to this training scheme as guiding the learning process of a curriculum NMT model by a pretrained vanilla model. In this paper, we assess the effectiveness of the proposed training scheme and take an insight into the influence of translation direction, evaluation metrics and different curriculum schedules. Experimental results on translation benchmarks WMT14 English ⇒ German, WMT17 Chinese ⇒ English and Multitarget TED Talks Task (MTTT) English ⇔ German, English ⇔ Chinese, English ⇔ Russian demonstrate that our proposed method consistently improves the translation performance against the advanced Transformer baseline.

In the research of machine reading comprehension of Japanese how-to tip QA tasks, conventional extractive machine reading comprehension methods have difficulty in dealing with cases in which the answer string spans multiple locations in the context. The method of fine-tuning of the BERT model for machine reading comprehension tasks is not suitable for such cases. In this paper, we trained a generative machine reading comprehension model of Japanese how-to tip by constructing a generative dataset based on the website “wikihow” as a source of information. We then proposed two methods for multi-task learning to fine-tune the generative model. The first method is the multi-task learning with a generative and extractive hybrid training dataset, where both generative and extractive datasets are simultaneously trained on a single model. The second method is the multi-task learning with the inter-sentence semantic similarity and answer generation, where, drawing upon the answer generation task, the model additionally learns the distance between the sentences of the question/context and the answer in the training examples. The evaluation results showed that both of the multi-task learning methods significantly outperformed the single-task learning method in generative question-and-answer examples. Between the two methods for multi-task learning, that with the inter-sentence semantic similarity and answer generation performed the best in terms of the manual evaluation result. The data and the code are available at https://github.com/EternalEdenn/multitask_ext-gen_sts-gen.

We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.

This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among speaker characteristics, along with acoustic features such as F0, for reproducing individual utterances in speech synthesis. A novel feature of the proposed method is the rhythm-based embeddings extracted from phonemes and their durations, which are known to be related to speaking rhythm. They are extracted with a speaker identification model similar to the conventional spectral feature-based one. We conducted three experiments, speaker embeddings generation, speech synthesis with generated embeddings, and embedding space analysis, to evaluate the performance. The proposed method demonstrated a moderate speaker identification performance (15.2% EER), even with only phonemes and their duration information. The objective and subjective evaluation results demonstrated that the proposed method can synthesize speech with speech rhythm closer to the target speaker than the conventional method. We also visualized the embeddings to evaluate the relationship between the distance of the embeddings and the perceptual similarity. The visualization of the embedding space and the relation analysis between the closeness indicated that the distribution of embeddings reflects the subjective and objective similarity.

The goal of Acoustic Scene Classification (ASC) is to simulate human analysis of the surrounding environment and make accurate decisions promptly. Extracting useful information from audio signals in real-world scenarios is challenging and can lead to suboptimal performance in acoustic scene classification, especially in environments with relatively homogeneous backgrounds. To address this problem, we model the sobering-up process of “drunkards” in real-life and the guiding behavior of normal people, and construct a high-precision lightweight model implementation methodology called the “drunkard methodology”. The core idea includes three parts: (1) designing a special feature transformation module based on the different mechanisms of information perception between drunkards and ordinary people, to simulate the process of gradually sobering up and the changes in feature perception ability; (2) studying a lightweight “drunken” model that matches the normal model's perception processing process. The model uses a multi-scale class residual block structure and can obtain finer feature representations by fusing information extracted at different scales; (3) introducing a guiding and fusion module of the conventional model to the “drunken” model to speed up the sobering-up process and achieve iterative optimization and accuracy improvement. Evaluation results on the official dataset of DCASE2022 Task1 demonstrate that our baseline system achieves 40.4% accuracy and 2.284 loss under the condition of 442.67K parameters and 19.40M MAC (multiply-accumulate operations). After adopting the “drunkard” mechanism, the accuracy is improved to 45.2%, and the loss is reduced by 0.634 under the condition of 551.89K parameters and 23.6M MAC.

Photo animation is to transform photos of real-world scenes into anime style images, which is a challenging task in AIGC (AI Generated Content). Although previous methods have achieved promising results, they often introduce noticeable artifacts or distortions. In this paper, we propose a novel double-tail generative adversarial network (DTGAN) for fast photo animation. DTGAN is the third version of the AnimeGAN series. Therefore, DTGAN is also called AnimeGANv3. The generator of DTGAN has two output tails, a support tail for outputting coarse-grained anime style images and a main tail for refining coarse-grained anime style images. In DTGAN, we propose a novel learnable normalization technique, termed as linearly adaptive denormalization (LADE), to prevent artifacts in the generated images. In order to improve the visual quality of the generated anime style images, two novel loss functions suitable for photo animation are proposed: 1) the region smoothing loss function, which is used to weaken the texture details of the generated images to achieve anime effects with abstract details; 2) the fine-grained revision loss function, which is used to eliminate artifacts and noise in the generated anime style image while preserving clear edges. Furthermore, the generator of DTGAN is a lightweight generator framework with only 1.02 million parameters in the inference phase. The proposed DTGAN can be easily end-to-end trained with unpaired training data. Extensive experiments have been conducted to qualitatively and quantitatively demonstrate that our method can produce high-quality anime style images from real-world photos and perform better than the state-of-the-art models.

This paper proposes a novel application of coded apertures (CAs) for visual information hiding. CA is one of the representative computational photography techniques, in which a patterned mask is attached to a camera as an alternative to a conventional circular aperture. With image processing in the post-processing phase, various functions such as omnifocal image capturing and depth estimation can be performed. In general, a watermark embedded as high-frequency components is difficult to extract if captured outside the focal length, and defocus blur occurs. Installation of a CA into the camera is a simple solution to mitigate the difficulty, and several attempts are conducted to make a better design for stable extraction. On the contrary, our motivation is to design a specific CA as well as an information hiding scheme; the secret information can only be decoded if an image with hidden information is captured with the key aperture at a certain distance outside the focus range. The proposed technique designs the key aperture patterns and information hiding scheme through evolutionary multi-objective optimization so as to minimize the decryption error of a hidden image when using the key aperture while minimizing the accuracy when using other apertures. During the optimization process, solution candidates, i.e., key aperture patterns and information hiding schemes, are evaluated on actual devices to account for disturbances that cannot be considered in optical simulations. Experimental results have shown that decoding can be performed with the designed key aperture and similar ones, that decrypted image quality deteriorates as the similarity between the key and the aperture used for decryption decreases, and that the proposed information hiding technique works on actual devices.

In this paper, we present a novel photometric compensation network named CASEformer, which is built upon the Swin module. For the first time, we combine coordinate attention and channel attention mechanisms to extract rich features from input images. Employing a multi-level encoder-decoder architecture with skip connections, we establish multiscale interactions between projection surfaces and projection images, achieving precise inference and compensation. Furthermore, through an attention fusion module, which simultaneously leverages both coordinate and channel information, we enhance the global context of feature maps while preserving enhanced texture coordinate details. The experimental results demonstrate the superior compensation effectiveness of our approach compared to the current state-of-the-art methods. Additionally, we propose a method for multi-surface projection compensation, further enriching our contributions.

In this paper, we explore privacy-preserving techniques in federated learning, including those can be used with both neural networks and decision trees. We begin by identifying how information can be leaked in federated learning, after which we present methods to address this issue by introducing two privacy-preserving frameworks that encompass many existing privacy-preserving federated learning (PPFL) systems. Through experiments with publicly available financial, medical, and Internet of Things datasets, we demonstrate the effectiveness of privacy-preserving federated learning and its potential to develop highly accurate, secure, and privacy-preserving machine learning systems in real-world scenarios. The findings highlight the importance of considering privacy in the design and implementation of federated learning systems and suggest that privacy-preserving techniques are essential in enabling the development of effective and practical machine learning systems.

In this paper, the quality and transferred data based video bitrate control method for web-conferencing services is proposed, aiming to reduce transferred data by suppressing excessive quality. In web-conferencing services, the video bitrate is generally controlled in accordance with the network conditions (e.g., jitter and packet loss rate) to improve users' quality. However, in such a control, the bitrate is excessively high when the network conditions is sufficiently high (e.g., high throughput and low jitter), which causes an increased transferred data volume. The increased volume of data transferred leads to increased operational costs, such as network costs for service providers. To solve this problem, we developed a method to control the video bitrate of each user to achieve the required quality determined by the service provider. This method is implemented in an actual web-conferencing system and evaluated under various conditions. It was shown that the bitrate could be controlled in accordance with the required quality to reduce the transferred data volume.

This paper proposes user equipment (UE) grouping schemes and evaluates the performance of a scheduling scheme for each formed group in collaborative multiple-input multiple-output (MIMO) reception. In previous research, the criterion for UE grouping and the effects of group scheduling has never been presented. In the UE grouping scheme, two criteria, the base station (BS)-oriented one and the UE-oriented one, are presented. The BS-oriented full search scheme achieves ideal performance though it requires knowledge of the relative positions of all UEs. Therefore, the UE-oriented local search scheme is also proposed. As the scheduling scheme, proportional fairness scheduling is used in resource allocation for each formed group. When the number of total UEs increases, the difference in the number of UEs among groups enlarges. Numerical results obtained through computer simulation show that the throughput per user increases and the fairness among users decreases when the number of UEs in a cell increases in the proposed schemes compared to those of the conventional scheme.

Device-to-device (D2D) communication allows user terminals to directly communicate with each other without the need for any base stations (BSs). Since the D2D communication underlaying a cellular system shares frequency channels with BSs, co-channel interference may occur. Successive interference cancellation (SIC), which is also called the serial interference canceler, detects and subtracts user signals from received signals in descending order of received power, can cope with the above interference and has already been applied to fog nodes that manage communications among machine-to-machine (M2M) devices besides direct communications with BSs. When differences among received power levels of user signals are negligible, however, SIC cannot work well and thus causes degradation in bit error rate (BER) performance. To solve such a problem, this paper proposes to apply parallel interference cancellation (PIC), which can simultaneously detect both desired and interfering signals under the maximum likelihood criterion and can maintain good BER performance even when power level differences among users are small. When channel coding is employed, however, SIC can be superior to PIC in terms of BER under some channel conditions. Considering the superiority, this paper also proposes to select the proper cancellation scheme and modulation and coding scheme (MCS) that can maximize the throughput of D2D under a constraint of BER, in which the canceler selection is referred to as adaptive interference cancellation. Computer simulations show that PIC outperforms SIC under almost all channel conditions and thus the adaptive selection from PIC and SIC can achieve a marginal gain over PIC, while PIC can achieve 10% higher average system throughput than that of SIC. As for transmission delay time, it is demonstrated that the adaptive selection and PIC can shorten the delay time more than any other schemes, although the fog node causes the delay time of 1ms at least.

The application of millimeter wave (mmWave) directional transmission technology in high-speed railway (HSR) scenarios helps to achieve the goal of multiple gigabit data rates with low latency. However, due to the high mobility of trains, the traditional initial access (IA) scheme with high time consumption is difficult to guarantee the effectiveness of the beam alignment. In addition, the high path loss at the coverage edge of the millimeter wave remote radio unit (mmW-RRU) will also bring great challenges to the stability of IA performance. Fortunately, the train trajectory in HSR scenarios is periodic and regular. Moreover, the cell-free network helps to improve the system coverage performance. Based on these observations, this paper proposes an efficient IA scheme based on location and history information in cell-free networks, where the train can flexibly select a set of mmW-RRUs according to the received signal quality. We specifically analyze the collaborative IA process based on the exhaustive search and based on location and history information, derive expressions for IA success probability and delay, and perform the numerical analysis. The results show that the proposed scheme can significantly reduce the IA delay and effectively improve the stability of IA success probability.

The proportion of persons over 65 years old is projected to increase worldwide between 2022 and 2050. The increasing burden on medical staff and the shortage of human resources are growing problems. Bedsores are injuries caused by prolonged pressure on the skin and stagnation of blood flow. The more the damage caused by bedsores progresses, the longer the treatment period becomes. Moreover, patients require surgery in some serious cases. Therefore, early detection is essential. In our research, we are developing a non-contact bedsore detection system using electromagnetic waves at 10.5GHz. In this paper, we extracted appropriate information from a scalogram and utilized it to detect the sizes of bedsores. In addition, experiments using a phantom were conducted to confirm the basic operation of the bedsore detection system. As a result, using the approximate curves and lines obtained from prior analysis data, it was possible to estimate the volume of each defected area, as well as combinations of the depth of the defected area and the length of the defected area. Moreover, the experiments showed that it was possible to detect bedsore presence and estimate their sizes, although the detection results had slight variations.

This study investigates the improvement of the channel capacity of 5-GHz-band multiple-input multiple-output (MIMO) communication using microwave-guided modes propagating along a polyvinyl chloride (PVC) pipe wall for a buried pipe inspection robot. We design a planar Yagi-Uda antenna to reduce transmission losses in communication with PVC pipe walls as propagation paths. Coupling efficiency between the antenna and a PVC pipe is improved by attaching a PVC adapter with the same curvature as the PVC pipe's inner wall to the Yagi-Uda antenna to eliminate any gap between the antenna and the inner wall of the PVC pipe. The use of a planar Yagi-Uda antenna with a PVC adaptor decreases the transmission loss of a 5-GHz-band microwave signal propagating along a 1-m-lomg straight PVC pipe wall by 7dB compared to a dipole antenna. The channel capacity of a 2×2 MIMO system using planar Yagi-Uda antennas is more than twice that of the system using dipole antennas.

Mobile edge computing (MEC) is a key technology for providing services that require low latency by migrating cloud functions to the network edge. The potential low quality of the wireless channel should be noted when mobile users with limited computing resources offload tasks to an MEC server. To improve the transmission reliability, it is necessary to perform resource allocation in an MEC server, taking into account the current channel quality and the resource contention. There are several works that take a deep reinforcement learning (DRL) approach to address such resource allocation. However, these approaches consider a fixed number of users offloading their tasks, and do not assume a situation where the number of users varies due to user mobility. This paper proposes Deep reinforcement learning model for MEC Resource Allocation with Dummy (DMRA-D), an online learning model that addresses the resource allocation in an MEC server under the situation where the number of users varies. By adopting dummy state/action, DMRA-D keeps the state/action representation. Therefore, DMRA-D can continue to learn one model regardless of variation in the number of users during the operation. Numerical results show that DMRA-D improves the success rate of task submission while continuing learning under the situation where the number of users varies.

Information-Centric Networking (ICN) is an innovative technology that provides low-loss, low-latency, high-throughput, and high-reliability communications for diversified and advanced services and applications. In this article, we present a technical survey of ICN functionalities such as in-network caching, routing, transport, and security mechanisms, as well as recent research findings. We focus on CCNx, which is a prominent ICN protocol whose message types are defined by the Internet Research Task Force. To facilitate the development of functional code and encourage application deployment, we introduce an open-source software platform called Cefore that facilitates CCNx-based communications. Cefore consists of networking components such as packet forwarding and in-network caching daemons, and it provides APIs and a Python wrapper program that enables users to easily develop CCNx applications for on Cefore. We introduce a Mininet-based Cefore emulator and lightweight Docker containers for running CCNx experiments on Cefore. In addition to exploring ICN features and implementations, we also consider promising research directions for further innovation.