In real-time human-machine interaction (HMI) applications, hand gesture recognition (HGR) requires high accuracy with low latency. Surface electromyography (sEMG), a physiological electrical signal reflecting muscle activation, is extensively used in HMI. Recently, transient sEMG, generated during the gesture transitions, has been employed in HGR to achieve lower observational latency compared to steady-state sEMG. However, the use of long feature windows (up to 200 ms) still make it less desirable in low-latency HMI. In addition, most studies have relied on remote computing, where remote data processing and large data transfer result in high computation and network latency. In this paper, we proposed a method leveraging transient high density sEMG (HD-sEMG) and in-sensor computing to achieve low-latency HGR. An sEMG contrastive convolution network (sCCN) was proposed for HGR. The mean absolute value and its average integration were used to train the sCCN in a contrastive learning manner. In addition, all signal acquisition, data processing, and pattern recognition processes were deployed within designed sensor for in-sensor computing. Compared to the state-of-the-art study using multi-channel 200-ms transient sEMG, our proposed method achieved a comparable HGR accuracy of 0.963, and a 58% lower observational latency of only 84 ms. In-sensor computing realizes a 4 times lower computation latency of 3 ms, and significantly reduces the network latency to 2 ms. The proposed method offers a promising approach to achieving low-latency HGR without compromising accuracy. This facilitates real-time HMI in biomedical applications such as prostheses, exoskeletons, virtual reality, and video games.

As deep learning (DL) technologies become ubiquitous, GPU clusters are deployed for inference tasks with consistent service level objectives (SLOs). Efficiently utilizing multiple GPUs is crucial for throughput and cost-effectiveness. This article addresses the challenges posed by dynamic input and NVIDIA MIG in scheduling DL workloads. We present ElasticBatch, a scheduling system that simplifies configuration through bucketization and employs a machine learning-based pipeline to optimize settings. Our experiments demonstrate that ElasticBatch achieves a 50% reduction in GPU instances compared to MIG disablement, increases GPU utilization by 1.4% to 6.5% over an ideal scheduler and significantly reduces profiling time. This research contributes to the discourse on efficient utilization of GPU clusters. ElasticBatch's effectiveness in mitigating challenges posed by dynamic inputs and NVIDIA MIG underscores its potential to optimize GPU cluster performance, providing tangible benefits in terms of reduced instances, increased utilization, and significant time savings in real-world deployment scenarios.

Recent advances in generative adversarial networks (GANs) have provided potential solutions for photo-realistic human image synthesis. However, the explicit and individual control of synthesis over multiple factors, such as poses, body shapes, and skin colors, remains difficult for existing methods. This is because current methods mainly rely on a single pose/appearance model, which is limited in dis-entangling various poses and appearance in human images. In addition, such a unimodal strategy is prone to causing severe artifacts in the generated images like color distortions and unrealistic textures. To tackle these issues, this paper proposes a multi-factor conditioned method dubbed BodyGAN. Specifically, given a source image, our Body-GAN aims at capturing the characteristics of the human body from multiple aspects: (i) A pose encoding branch consisting of three hybrid subnetworks is adopted, to generate the semantic segmentation based representation, the 3D surface based representation, and the key point based rep-resentation of the human body, respectively. (ii) Based on the segmentation results, an appearance encoding branch is used to obtain the appearance information of the human body parts. (iii) The outputs of these two branches are represented by user-editable condition maps, which are then processed by a generator to predict the synthesized image. In this way, our BodyGAN can achieve the fine-grained dis-entanglement of pose, body shape, and appearance, and consequently enable the explicit and effective control of syn-thesis with diverse conditions. Extensive experiments on multiple datasets and a comprehensive user study show that our BodyGAN achieves the state-of-the-art performance.

In this paper, we present a class of hybrid coupled serially concatenated codes (HC-SCC), in which coupling is achieved by re-encoding partial outputs from both the outer and the inner encoders. Firstly, we derive the exact density evolution (DE) equations over the binary erasure channels (BECs) for the HC-SCCs, which can be used to analyze the impact of the coupling ratios and the coupling memories on the performances of the HC-SCCs. Secondly, we present a genie-aided lower bound for the proposed HC-SCCs to estimate their error-floors. Thirdly, we use the DE equations to design randomly punctured HC-SCCs, including rate-compatible HC-SCCs. The analytical and the numerical results show that: 1) for comparable coupling memories, the iterative decoding thresholds of the proposed HC-SCC ensembles are better than those of the recently introduced spatially coupled serially concatenated code (SC-SCC) ensembles and the partially parity-coupled turbo code (PPC-TC) ensembles; 2) with outer coupling memory five and inner coupling memory five, the iterative decoding thresholds of the rate-compatible HC-SCCs over the BECs are 0.0003 away from the corresponding channel capacities for a wide range of coding rates; 3) simulation results over the additive white Gaussian noise (AWGN) channels and the BECs are provided to confirm the performance advantages of the HC-SCCs. Particularly, the simulation results show that the HC-SCCs admit lower error-floor than the SC-SCCs and the rate-compatible HC-SCCs perform better than the PPC-TCs, which are consistent with the results of DE analysis.