arXiv subjects

Ziyang Song

Publications and source records attributed to Ziyang Song.

45 records · Page 3Linked to original sources

arXiv2023

Secure HARQ-IR-Aided Terahertz Communications

Terahertz (THz) communication is one of the most promising candidates to accommodate high-speed mobile data services. This paper proposes a secure hybrid automatic repeat request with incremental redundancy (HARQ-IR) aided THz communication scheme, where the transmission secrecy is ensured by confusing the eavesdropper with dummy messages. The connection and secrecy outage probabilities are then derived in closed-form. Besides, the tail behaviour of the connection outage probability in high signal-to-noise ratio (SNR) is examined by carrying out the asymptotic analysis, and the upper bound of the secrecy outage probability is obtained in a simple form by capitalizing on large deviations. With these results, we take a step further to investigate the secrecy long term average throughput (LTAT). By noticing that HARQ-IR not only improves the reliability of the legitimate user, but also increases the probability of being eavesdropped, a robust rate adaption policy is finally proposed to maximize the LTAT while restricting the connection and secrecy outage probabilities within satisfactory requirements.

cs.IT↗

arXiv2023

Performance Analysis and Optimal Design of HARQ-IR-Aided Terahertz Communications

Terahertz (THz) communications are envisioned to be a promising technology for 6G thanks to its broad bandwidth. However, the large path loss, antenna misalignment, and atmospheric influence of THz communications severely deteriorate its reliability. To address this, hybrid automatic repeat request (HARQ) is recognized as an effective technique to ensure reliable THz communications. This paper delves into the performance analysis of HARQ with incremental redundancy (HARQ-IR)-aided THz communications in the presence/absence of blockage. More specifically, the analytical expression of the outage probability of HARQ-IR-aided THz communications is derived, with which the asymptotic outage analysis is enabled to gain meaningful insights, including diversity order, power allocation gain, modulation and coding gain, etc. Then the long term average throughput (LTAT) is expressed in terms of the outage probability based on renewal theory. Moreover, to combat the blockage effects, a multi-hop HARQ-IR-aided THz communication scheme is proposed and its performance is examined. To demonstrate the superiority of the proposed scheme, the other two HARQ-aided schemes, i.e., Type-I HARQ and HARQ with chase combining (HARQ-CC), are used for benchmarking in the simulations. In addition, a deep neural network (DNN) based outage evaluation framework with low computational complexity is devised to reap the benefits of using both asymptotic and simulation results in low and high outage regimes, respectively. This novel outage evaluation framework is finally employed for the optimal rate selection, which outperforms the asymptotic based optimization.

cs.IT↗

arXiv2022

ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders. To further facilitate research on multi-person motion generation, we introduce a new synthetic dataset of complex multi-person combat behaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and the proposed combat dataset show that our method can adapt to various human motion representations and achieve superior performance over the state-of-the-art methods on both single-person and multi-person motion generation tasks, demonstrating a promising step towards a general human motion generator.

cs.CV↗

arXiv2022

OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike all existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method, called OGC, to simultaneously identify multiple 3D objects in a single forward pass, without needing any type of human annotations. The key to our approach is to fully leverage the dynamic motion patterns over sequential point clouds as supervision signals to automatically discover rigid objects. Our method consists of three major components, 1) the object segmentation network to directly estimate multi-object masks from a single point cloud frame, 2) the auxiliary self-supervised scene flow estimator, and 3) our core object geometry consistency component. By carefully designing a series of loss functions, we effectively take into account the multi-object rigid consistency and the object shape invariance in both temporal and spatial scales. This allows our method to truly discover the object geometry even in the absence of annotations. We extensively evaluate our method on five datasets, demonstrating the superior performance for object part instance segmentation and general object segmentation in both indoor and the challenging outdoor scenarios.

cs.CV↗

arXiv2022

Outage Probability Analysis of HARQ-Aided Terahertz Communications

Although terahertz (THz) communications can provide mobile broadband services, it usually has a large path loss and is vulnerable to antenna misalignment. This significantly degrades the reception reliability. To address this issue, the hybrid automatic repeat request (HARQ) is proposed to further enhance the reliability of THz communications. This paper provides an in-depth investigation on the outage performance of two different types of HARQ-aided THz communications, including Type-I HARQ and HARQ with chase combining (HARQ-CC). Moreover, the effects of both fading and stochastic antenna misalignment are considered in this paper. The exact outage probabilities of HARQ-aided THz communications are derived in closed-form, with which the asymptotic outage analysis is enabled to explore helpful insights. In particular, it is revealed that full time diversity can be achieved by using HARQ assisted schemes. Besides, the HARQ-CC-aided scheme performs better than the Type-I HARQ-aided one due to its high diversity combining gain. The analytical results are eventually validated via Monte-Carlo simulations.

cs.IT↗

arXiv2021

Multi-scale Matching Networks for Semantic Correspondence

Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn discriminative pixel-level features for semantic correspondence. In this paper, we propose a multi-scale matching network that is sensitive to tiny semantic differences between neighboring pixels. We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks. During feature enhancement, intra-scale enhancement fuses same-resolution feature maps from multiple layers together via local self-attention and cross-scale enhancement hallucinates higher-resolution feature maps along the top-down hierarchy. Besides, we learn complementary matching details at different scales thus the overall matching score is refined by features of different semantic levels gradually. Our multi-scale matching network can be trained end-to-end easily with few additional learnable parameters. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on three popular benchmarks with high computational efficiency.

cs.CV↗

arXiv2021

Supervised multi-specialist topic model with applications on large-scale electronic health record data

Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a closed-form collapsed variational inference algorithm to learn the model distributions of MixEHR-S. We applied MixEHR-S to two independent large-scale EHR databases in Quebec with three targeted applications: (1) Congenital Heart Disease (CHD) diagnostic prediction among 154,775 patients; (2) Chronic obstructive pulmonary disease (COPD) diagnostic prediction among 73,791 patients; (3) future insulin treatment prediction among 78,712 patients diagnosed with diabetes as a mean to assess the disease exacerbation. In all three applications, MixEHR-S conferred clinically meaningful latent topics among the most predictive latent topics and achieved superior target prediction accuracy compared to the existing methods, providing opportunities for prioritizing high-risk patients for healthcare services. MixEHR-S source code and scripts of the experiments are freely available at https://github.com/li-lab-mcgill/mixehrS

cs.LG↗

arXiv2020

Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation

In recognition-based action interaction, robots' responses to human actions are often pre-designed according to recognized categories and thus stiff. In this paper, we specify a new Interactive Action Translation (IAT) task which aims to learn end-to-end action interaction from unlabeled interactive pairs, removing explicit action recognition. To enable learning on small-scale data, we propose a Paired-Embedding (PE) method for effective and reliable data augmentation. Specifically, our method first utilizes paired relationships to cluster individual actions in an embedding space. Then two actions originally paired can be replaced with other actions in their respective neighborhood, assembling into new pairs. An Act2Act network based on conditional GAN follows to learn from augmented data. Besides, IAT-test and IAT-train scores are specifically proposed for evaluating methods on our task. Experimental results on two datasets show impressive effects and broad application prospects of our method.

cs.CV↗

arXiv2020

Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task in interaction scenarios and propose an attention-oriented multi-level network framework to meet the need for real-time interaction. Specifically, a Pre-Attention network is employed to roughly focus on the interactor in the scene at low resolution firstly and then perform fine-grained pose estimation at high resolution. The other compact CNN receives the extracted skeleton sequence as input for action recognition, utilizing attention-like mechanisms to capture local spatial-temporal patterns and global semantic information effectively. To evaluate our approach, we construct a new action dataset specially for the recognition task in interaction scenarios. Experimental results on our dataset and high efficiency (112 fps at 640 x 480 RGBD) on the mobile computing platform (Nvidia Jetson AGX Xavier) demonstrate excellent applicability of our method on action recognition in real-time human-robot interaction.

cs.CV↗