Existing methods for cross-component prediction focus on the chroma intra pre-diction but neglect the chroma prediction across multiple frames. In this paper, we propose a novel compression framework that leverages chroma frame sampling and inter-frame chroma prediction to address this problem. Specifically, chroma frame sampling discards the chroma components in inter-predicted frames to further reduce the bit consumption, whereas inter-frame chroma prediction recovers the discarded chroma components with optical flow estimation and post-training optimization for a guaranteed fidelity. To our best knowledge, this paper is the first attempt to achieve deep learning-based inter prediction of chroma components. To accommodate the proposed framework, we redesign the HEVC codec to enable hybrid coding of luma and chroma components. Experimental results show that the proposed framework achieves up to 0.76% BD-rate reduction when compared to standard HEVC.

Recent video colorization methods optimize correspondence estimation and information propagation in an end-to-end manner. However, they usually suffer from loss of fidelity due to the inaccurate inference of correspondence measurement. In this paper, we propose a post-training optimization (PTO) strategy to refine correspondence measurement in the end-to-end optimized framework. The proposed PTO strategy introduces a pseudo loss function to well approximate the target loss and guide the direction of updates. We further develop a video colorization method that incorporates PTO and optical flow to guarantee high-fidelity colorized frames in theory. Experimental results demonstrate that the proposed method achieves state-of-the-art PSNR performance in video colorization on the DAVIS dataset and common test sequences for video coding. Furthermore, the proposed method can be employed into video compression and achieves competitive rate-distortion performance with the recent High Efficiency Video Coding (HEVC) standard.

Remote direct memory access (RDMA) has been employed to boost remote data access for key-value stores, since it provides kernel-bypass, zero-copy and low-latency features. Meanwhile, existing RDMA-enabled key-value stores still have performance bottlenecks, since extra costs need to be spent on processing requests and keeping data consistency. This paper introduces Reno, an RDMA-enabled, NVM-optimized key-value store that supports fast remote access of persistent data. On the server-side, Reno is built atop a bucket-based hopscotch hash table, where the actual key-value items are stored in NVM (non-volatile memories), and metadata are managed by an in-DRAM index. On the client-side, Reno adopts a fully server-bypass paradigm for both remote read and write requests to achieve low latency and high throughput. We evaluate Reno on an Intel's Optane DC Persistent Memory platform with Infiniband network support. The results show the strengths of Reno. In particular, Reno outperforms its counterparts by 1.1~3.3x for remote reads and 1.9~4.8 x for remote writes in terms of latency; the speedups of concurrent throughput are up to 2.33 x, 2.36 x, 3.09 x and 5.08 x for read-only, read-heavy, write-heavy and write-only YCSB workloads, respectively.

This paper presents direct sequence spread spectrum (DS/SS) datalinks operating at 92-100 GHz with spreading factors up to 100K. Unlike traditional DS/SS datalinks which rely on preamble and cyclic dispreading for synchronization, the reported datalink uses a self-synchronous demodulation scheme, avoiding the large hardware complexity associated with exceptionally large spreading factors, and avoiding the difficulties of synchronizing the long de-spreading codes that are applicable to mm-wave systems. A demonstration link chipset is presented operating at 92-100 GHz with a spreading factor of 104K and a spread bandwidth of 6.0 GHz (baseband bandwidth of 56Kb/s) while consuming a total of 425mW.

In this paper, we propose a multi-modal multi-feature (M$^{3}F$) approach for in-the-wild valence-arousal estimation. In the proposed M$^{3}F$ framework, we fuse both visual features from videos and acoustic features from the audio tracks to estimate the valence and arousal. We follow a CNN-RNN paradigm, where the spatio-temporal visual features are extracted with a 3D convolutional network and/or a pretrained 2D convolutional network, and a bidirectional recurrent neural network. We evaluated the M$^{3}F$ framework on the validation set provided by the Affective Behavior Analysis in-the-wild (ABAW) Challenge, held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020, and it significantly outperforms the baseline method.

This brief presents a wireline transmitter architecture, enabling multilevel signaling with feedforward equalization (FFE) in voltage-mode. A compact R2R-DAC-based front end is proposed and analyzed in terms of its speed, power consumption, and linearity. A voltage-mode PAM-4 transmitter with 2-tap FFE utilizing the proposed architecture is implemented in the 65-nm CMOS technology. It achieves a data rate of 34 Gb/s and an energy efficiency of 2.7 mW/Gb/s.

As an effective environment representation method, the obstacle occupancy grid has been widely applied on the autonomous vehicle, providing evidence for the behavior decision and path planning of autonomous vehicle. In this paper, a new obstacle occupancy grid named space-time occupancy grid map is presented. This map pays more attention on the dynamic obstacles in a period of future time, and maps the obstacle occupancy information in space-time dimension to two-dimensional grid. In this way, the useful obstacle occupancy information for the autonomous vehicle in a period of future time is provided, which enables the behavior decision and path planning to be more intelligent. The space-time occupancy grid map described in this paper has been applied on the two generations of autonomous vehicles, “Intelligent Pioneer I” and “Intelligent Pioneer II”, which have already completed 10,000 kilometers actual road tests in western suburb of Hefei, and won the first prize in the “Intelligent Vehicle Future Challenge of China” Competition funded by Natural Science Foundation of China.