This paper studies the early hybrid automatic repeat request (E-HARQ) in the 5G new radio (NR). The earliest ARQ feedback to the transmitter within 0.2 msec, suitable for ultra-reliable-low-latency (URLLC) services, happens when the feedback indicates retransmission or a new data request is sent before the decoding process. In this case, the feedback is based on predicting the decoding outcome of the codeword bits sent as symbols with a specific modulation and coding scheme (MCS). Existing state-of-the-art neural network-based E-HARQ predictor exploits log-likelihood-ratio (LLR), calculated by the symbol detector, to predict ARQ feedback. They also did not include MCS as an input, so individual predictors are needed for different MCSs. This paper proposes a single NN-based E-HARQ predictor for different MCSs. The predictor has a single hidden layer, and it uses the channel estimates, the MCS information, the redundancy versions, and the approximate probability distribution function of LLRs at the receiver as inputs to predict decoding outcomes. Simulation results show that the proposed predictor reduces the latency of existing NN-based E-HARQ predictors and traditional HARQ by 46% and 60%, respectively. Its complexity is shown to be, on average, 99% lower than other predictors.

Speech separation aims to extract multiple speech sources from mixed signals. In this paper, we propose SepDiff - a monaural speech separation method based on the denoising diffusion model (diffusion model). By modifying the diffusion and reverse process, we show that the diffusion model achieves an impressive performance on speech separation. To generate speech sources, we use mel spectrogram of the mixture as a condition in the training procedure and insert it in every step of the sampling procedure. We propose a novel DNN structure to leverage local and global speech information through successive feature channel attention and dilated 2-D convolution blocks on multi-resolution time-frequency features. We use a neural vocoder to get waveform from the generated mel spectrogram. We evaluate SepDiff on LibriMix datasets. Compared to SepFormer approach, SepDiff yields a higher mean opinion score (MOS) of 0.11.

In recent years, the related research of entity alignment has mainly focused on entity alignment via knowledge embeddings and graph neural networks; however, these proposed models usually suffer from structural heterogeneity and the large-scale problem of knowledge graph. A novel entity alignment model based on graph isomorphic network and compressed sensing is proposed. First, for the problem of structural heterogeneity, graph isomorphic network encoder is applied in knowledge graph to capture structural similarity of entity relation. Second, for the problem of large scale, key node and community are integrated for priority entity alignment to improve execution speed. However, the exiting node importance ranking algorithm cannot accurately identify key node in knowledge graph. So the compressed sensing is adopted in node importance ranking to improve the accuracy of identifying key node. The authors have carried out several experiments to test the effect and efficiency of the proposed entity alignment model.

Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance is degraded when the scanned points deviate from the ideal conditions of cleanness and completeness. Important progress has been recently made by data-driven approaches, which learn global and/or local models of implicit surface representations from auxiliary sets of training shapes. Motivated from a universal phenomenon that self-similar shape patterns of local surface patches repeat across the entire surface of an object, we aim to push forward the data-driven strategies and propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface for a direct surface reconstruction from raw point cloud; we also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches. Given that orientations of raw points could be unavailable or noisy, we extend signagnostic learning into our local implicit model, which enables our recovery of signed implicit fields of local surfaces from the unsigned inputs. We term our framework as Sign-Agnostic Implicit Learning of Surface Self-Similarities (SAIL-S3). With a global post-optimization of local sign flipping, SAIL-S3 is able to directly model raw, un-oriented point clouds and reconstruct high-quality object surfaces. Experiments show its superiority over existing methods.

This paper proposes a novel approach for pose transfer, which aims at transferring the pose of a given person to a target pose. Unlike previous works directly simulating the target pose, we emphasize the pose geometric constraint in our approach to tackle this task. To capture the geometric constraints among the condition pose and target pose, we generate a sequence of different intermediate pose skeleton. Moreover, we introduced the 3D convolution into the generator of our Generative Adversarial Network (GAN) in order to learn spatiotemporal features from the generated pose skeleton sequence. The final target pose will be estimated and refined by a pose transfer block and a series of residual blocks based on the spatiotemporal features. Compared with the existing works, our generated person pose images achieved better performance in terms of Inception Score and Structure Similarity. Extensive experiments on dataset Market-1501 demonstrate the effectiveness of the pose skeleton sequence on pose transfer.

Summary The emergence of big data makes more and more enterprise change data management strategy, from simple data storage to OLAP query analysis; meanwhile, NoSQL‐based data warehouse receive more increasing attention than traditional SQL‐based database. By improving the JFSS model for ETL, this paper proposes the uniform distribution code (UDC), model identification code (MIC), standard dimension code (SDC), and attribute dimensional code (ADC); defines the data storage format of ; and identifies the extraction, transformation, and loading strategies of data warehouse. Several experiments are carried out to analyze single record and range record queries as typical OLAP based on Hadoop database (HBase). The results show the proposed scheme can provide lower overhead than the traditional SQL‐based database while facilitating the scope and flexibility of data warehouse services.