This paper presents an energy-efficient spike-sorting system-on-chip (SoC) designed for closed-loop brain-computer interfaces of massive probing channels. The design first incorporates a sparsity/similarity-aware spike detection scratchpad, leveraging a bit-wise differential encoder and zero-friendly read-out circuits, reducing the dynamic power consumption of spike detection by 77.7%. To mitigate static power dissipation, it also introduces an ultra-low-leakage dual-voltage 5T-SRAM array with level-shifter embedded sense amplifiers, achieving an 82.2% leakage power reduction of neural signal buffering by applying half$V_{DD}$on SRAM cells. Additionally, a memory hierarchy architecture combining on-chip SRAM and off-chip FeRAM, along with a firing-rate-based Osort for cluster template management, minimizes off-chip memory access to only 9.7% with a latency of$11.7\mu $s for 1024-channel spike sorting. A silicon prototype is fabricated in 28-nm CMOS technology, which achieves a power consumption of 583nW/channel and an area consumption of 0.0012mm2/channel. The chip supports real-time spike sorting with up to 16K templates,$21.3\times $greater than the state-of-the-art spike-sorting processor.

The main goal of image super-resolution is to create high-resolution (HR) images from low-resolution (LR) ones while maintaining clarity and accurate texture details. However, existing methods still suffer from issues such as lacking fine texture details and excessive smoothing. To address these issues, we propose an adaptive residual scaling generative adversarial network (ARSGAN) for image super-resolution. Specifically, we designed Adaptive Residual Scaling (ARS) mechanism that allows dynamic adjustment of the scaling factor, enabling the model to automatically optimize the fusion of residual information according to the features of the input image. In addition, we coupled Strip Attention to accurately capture image directional features, enhancing the model’s ability to capture long-range dependencies. We have also improved the discriminator by incorporating Linear Deformable Convolution (LDConv), which enhances the model’s ability to handle complex deformations and details. The experimental results demonstrate that ARSGAN achieves superior performance and visually pleasing results.

Sound speed profile (SSP) distribution is an important parameter for underwater positioning, navigation and timing (PNT) because it affects the propagation mode of underwater acoustic signals. To accurately predict future sound speed distribution, we propose a hierarchical long short–term memory (H–LSTM) neural network, which explores the distribution pattern of sound velocity in the time dimension. To verify the feasibility and effectiveness, we conducted both simulations and real experiments. The ocean experiment was held in the South China Sea in April 2023. Results show that the predictive error of the proposed method is only 0.1530 m/s, demonstrating the proposed method outperforms the state–of–the–art methods, and providing additional evidence of its heightened predictive capability in predicting future sound speed distribution.

High-precision time-to-digital converters (TDCs) are key components for controlling quantum systems and FPGAs have gained popularity for this task thanks to their low-cost and flexibility compared with Application Specific Integrated Circuits (ASICs). This paper investigates a novel FPGA-based TDC architecture that combines a wave union launcher and delay lines constructed with DSP blocks. The configuration achieves a 8.07ps RMS resolution on a low-cost Zynq FPGA with a power usage of only 0.628W. The low power consumption is achieved thanks to a combination of operating frequency and logic resource usage that are lower than other methods, such as multi-chain DSP based TDCs and multi-chain CARRY4 based TDCs.

The low frame rate and high latency of consumer depth cameras limits their use in interactive applications. We propose combining the Kinect depth camera with an ordinary color camera to synthesize a high frame rate and low latency depth image. We exploit common CMOS camera region of interest (ROI) functionality to obtain a high frame rate image over a small ROI. Motion in the ROI is computed by a fast optical flow implementation. The resulting flow field is used to extrapolate Kinect depth images to achieve high frame rate and low latency depth, and optionally predict depth to further reduce latency. Our "Hybrid HFR Depth" prototype generates useful depth images at maximum 500Hz with minimum 20ms latency. We demonstrate Hybrid HFR Depth in tracking fast moving objects, handwriting in the air, and projecting onto moving hands. Based on commonly available cameras and image processing implementations, Hybrid HFR Depth may be useful to HCI practitioners seeking to create fast, fluid depth camera-based interactions.

Colorization is an ambiguous problem, with multiple viable colorizations for a single grey-level image. However, previous methods only produce the single most probable colorization. Our goal is to model the diversity intrinsic to the problem of colorization and produce multiple colorizations that display long-scale spatial co-ordination. We learn a low dimensional embedding of color fields using a variational autoencoder (VAE). We construct loss terms for the VAE decoder that avoid blurry outputs and take into account the uneven distribution of pixel colors. Finally, we build a conditional model for the multi-modal distribution between grey-level image and the color field embeddings. Samples from this conditional model result in diverse colorization. We demonstrate that our method obtains better diverse colorizations than a standard conditional variational autoencoder (CVAE) model, as well as a recently proposed conditional generative adversarial network (cGAN).

We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that our construction is difficult to defeat, and show experimentally that our method is hard to defeat with both Type I and Type II attacks using several standard networks and datasets. This SafetyNet architecture is used to an important and novel application SceneProof, which can reliably detect whether an image is a picture of a real scene or not. SceneProof applies to images captured with depth maps (RGBD images) and checks if a pair of image and depth map is consistent. It relies on the relative difficulty of producing naturalistic depth maps for images in post processing. We demonstrate that our SafetyNet is robust to adversarial examples built from currently known attacking approaches.

We describe a method to produce detailed high resolution depth maps from aggressively subsampled depth measurements. Our method fully uses the relationship between image segmentation boundaries and depth boundaries It uses an image combined with a low resolution depth map. 1) The image is segmented with the guidance of sparse depth samples 2) Each segment has its depth field reconstructed independently using a novel smoothing method. 3) For videos, time-stamped samples from near frames are incorporated. The paper shows reconstruction results of super resolution from x4 to x100, while previous methods mainly work on x2 to xl6. The method is tested on four different datasets and six video sequences, covering quite different regimes, and it outperforms recent state of the art methods quantitatively and qualitatively We also demonstrate that depth maps produced by our method can be used by applications such as hand trackers, while depth maps from other methods have problems.

Driven by the advance of positioning technology and the popularity of location-sharing services, semantic-enriched trajectory data have become unprecedentedly available. The sequential patterns hidden in such data, when properly defined and extracted, can greatly benefit tasks like targeted advertising and urban planning. Unfortunately, classic sequential pattern mining algorithms developed for transactional data cannot effectively mine patterns in semantic trajectories, mainly because the places in the continuous space cannot be regarded as independent "items". Instead, similar places need to be grouped to collaboratively form frequent sequential patterns. That said, it remains a challenging task to mine what we call fine-grained sequential patterns , which must satisfy spatial compactness, semantic consistency and temporal continuity simultaneously. We propose Splitter to effectively mine such fine-grained sequential patterns in two steps. In the first step, it retrieves a set of spatially coarse patterns, each attached with a set of trajectory snippets that precisely record the pattern's occurrences in the database. In the second step, Splitter breaks each coarse pattern into fine-grained ones in a top-down manner, by progressively detecting dense and compact clusters in a higher-dimensional space spanned by the snippets. Splitter uses an effective algorithm called weighted snippet shift to detect such clusters, and leverages a divide-and-conquer strategy to speed up the top-down pattern splitting process. Our experiments on both real and synthetic data sets demonstrate the effectiveness and efficiency of Splitter.

Special-purpose group editors remain underused despite significant work over the past two decades.This paper proposes a novel approach to transparently adapting familiar single-user editors for group editing without modifying their source code. It only needs to adapt single-user editors to support two simple interfaces that get and set their states; edit scripts are derived between document states by diffing and concurrent scripts are merged on the fly. The approach is significantly less expensive than recent alternatives because it no longer needs to translate editing operations at the windows event level. The users are free to use any editing commands and even heterogeneous single-user editors can be used in the same group editing task. This work is part of a project called intelligent collaboration transparency (ICT).