arXiv subjects

Guangyu Li

Publications and source records attributed to Guangyu Li.

35 records · Page 2Linked to original sources

arXiv2024

A comprehensive framework for occluded human pose estimation

Occlusion presents a significant challenge in human pose estimation. The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively challenging. 2) Feature: Occlusion can cause feature confusion due to the high similarity between the target person and interfering individuals. 3) Inference: Robust inference becomes challenging due to the loss of complete body structural information. The existing methods designed for occluded human pose estimation usually focus on addressing only one of these factors. In this paper, we propose a comprehensive framework DAG (Data, Attention, Graph) to address the performance degradation caused by occlusion. Specifically, we introduce the mask joints with instance paste data augmentation technique to simulate occlusion scenarios. Additionally, an Adaptive Discriminative Attention Module (ADAM) is proposed to effectively enhance the features of target individuals. Furthermore, we present the Feature-Guided Multi-Hop GCN (FGMP-GCN) to fully explore the prior knowledge of body structure and improve pose estimation results. Through extensive experiments conducted on three benchmark datasets for occluded human pose estimation, we demonstrate that the proposed method outperforms existing methods. Code and data will be publicly available.

cs.CV↗

arXiv2023

Design of JiuTian Intelligent Network Simulation Platform

This paper introduced the JiuTian Intelligent Network Simulation Platform, which can provide wireless communication simulation data services for the Open Innovation Platform. The platform contains a series of scalable simulator functionalities, offering open services that enable users to use reinforcement learning algorithms for model training and inference based on simulation environments and data. Additionally, it allows users to address optimization tasks in different scenarios by uploading and updating parameter configurations. The platform and its open services were primarily introduced from the perspectives of background, overall architecture, simulator, business scenarios, and future directions.

cs.NI↗

arXiv2022

Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking

Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization. In this paper, we propose a novel point cloud registration-driven Siamese tracking framework, with the intuition that spatially aligned corresponding points (via 3D registration) tend to achieve consistent feature representations. Specifically, our method consists of two modules, including a tracking-specific nonlocal registration module and a registration-aided Sinkhorn template-feature aggregation module. The registration module targets at the precise spatial alignment between the template and search area. The tracking-specific spatial distance constraint is proposed to refine the cross-attention weights in the nonlocal module for discriminative feature learning. Then, we use the weighted SVD to compute the rigid transformation between the template and search area, and align them to achieve the desired spatially aligned corresponding points. For the feature aggregation model, we formulate the feature matching between the transformed template and search area as an optimal transport problem and utilize the Sinkhorn optimization to search for the outlier-robust matching solution. Also, a registration-aided spatial distance map is built to improve the matching robustness in indistinguishable regions (e.g., smooth surface). Finally, guided by the obtained feature matching map, we aggregate the target information from the template into the search area to construct the target-specific feature, which is then fed into a CenterPoint-like detection head for object localization. Extensive experiments on KITTI, NuScenes and Waymo datasets verify the effectiveness of our proposed method.

cs.CV↗

arXiv2022

Relativistic correction to the dissociation temperature of B_c mesons in the hot medium

By solving two body Dirac equations with potentials at finite temperature, we calculated the dissociation temperature T_d of B_c mesons in the quark-gluon plasma. It is found that the T_d becomes higher with the relativistic correction than the T_d from the Schroedinger equation. Both the short range interaction and the constant term of the potential at the long-range scale have a contribution to the shift of T_d, while the spin interaction is negligible.

nucl-th↗

arXiv2022

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

Recently, Graph Convolutional Network (GCN) has been widely used in Hyperspectral Image (HSI) classification due to its satisfactory performance. However, the number of labeled pixels is very limited in HSI, and thus the available supervision information is usually insufficient, which will inevitably degrade the representation ability of most existing GCN-based methods. To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed Contrastive Graph Convolutional Network (ConGCN), for HSI classification. First, in order to mine sufficient supervision signals from spectral information, a semi-supervised contrastive loss function is utilized to maximize the agreement between different views of the same node or the nodes from the same land cover category. Second, to extract the precious yet implicit spatial relations in HSI, a graph generative loss function is leveraged to explore supplementary supervision signals contained in the graph topology. In addition, an adaptive graph augmentation technique is designed to flexibly incorporate the spectral-spatial priors of HSI, which helps facilitate the subsequent contrastive representation learning. The extensive experimental results on four typical benchmark datasets firmly demonstrate the effectiveness of the proposed ConGCN in both qualitative and quantitative aspects.

cs.CV↗

arXiv2021

Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning

Edge caching will play a critical role in facilitating the emerging content-rich applications. However, it faces many new challenges, in particular, the highly dynamic content popularity and the heterogeneous caching configurations. In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning. Instead of trying to find a single dominating caching policy for all the caching scenarios, we employ an ensemble of constituent caching policies and adaptively select the best-performing policy to control the cache. Towards this goal, we first show through formal analysis and experiments that different variations of the LFU and LRU policies have complementary performance in different caching scenarios. We further develop a novel caching algorithm that enhances LFU/LRU with deep recurrent neural network (LSTM) based time-series analysis. Finally, we develop a deep reinforcement learning agent that adaptively combines base caching policies according to their virtual hit ratios on parallel virtual caches. Through extensive experiments driven by real content requests from two large video streaming platforms, we demonstrate that CEC not only consistently outperforms all single policies, but also improves the robustness of them. CEC can be well generalized to different caching scenarios with low computation overheads for deployment.

cs.NI↗

arXiv2020

Using Undersampling with Ensemble Learning to Identify Factors Contributing to Preterm Birth

In this paper, we propose Ensemble Learning models to identify factors contributing to preterm birth. Our work leverages a rich dataset collected by a NIEHS P42 Center that is trying to identify the dominant factors responsible for the high rate of premature births in northern Puerto Rico. We investigate analytical models addressing two major challenges present in the dataset: 1) the significant amount of incomplete data in the dataset, and 2) class imbalance in the dataset. First, we leverage and compare two types of missing data imputation methods: 1) mean-based and 2) similarity-based, increasing the completeness of this dataset. Second, we propose a feature selection and evaluation model based on using undersampling with Ensemble Learning to address class imbalance present in the dataset. We leverage and compare multiple Ensemble Feature selection methods, including Complete Linear Aggregation (CLA), Weighted Mean Aggregation (WMA), Feature Occurrence Frequency (OFA), and Classification Accuracy Based Aggregation (CAA). To further address missing data present in each feature, we propose two novel methods: 1) Missing Data Rate and Accuracy Based Aggregation (MAA), and 2) Entropy and Accuracy Based Aggregation (EAA). Both proposed models balance the degree of data variance introduced by the missing data handling during the feature selection process while maintaining model performance. Our results show a 42\% improvement in sensitivity versus fallout over previous state-of-the-art methods.

stat.AP↗

arXiv2019

Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network

In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the 'edge filter', so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches.

cs.LG↗

arXiv2019

D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios

Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models. We propose D$^2$-City, a large-scale comprehensive collection of dashcam videos collected by vehicles on DiDi's platform. D$^2$-City contains more than 10000 video clips which deeply reflect the diversity and complexity of real-world traffic scenarios in China. We also provide bounding boxes and tracking annotations of 12 classes of objects in all frames of 1000 videos and detection annotations on keyframes for the remainder of the videos. Compared with existing datasets, D$^2$-City features data in varying weather, road, and traffic conditions and a huge amount of elaborate detection and tracking annotations. By bringing a diverse set of challenging cases to the community, we expect the D$^2$-City dataset will advance the perception and related areas of intelligent driving.

cs.LG↗

arXiv2019

Automatic dimensionality selection for principal component analysis models with the ignorance score

Principal component analysis (PCA) is by far the most widespread tool for unsupervised learning with high-dimensional data sets. Its application is popularly studied for the purpose of exploratory data analysis and online process monitoring. Unfortunately, fine-tuning PCA models and particularly the number of components remains a challenging task. Today, this selection is often based on a combination of guiding principles, experience, and process understanding. Unlike the case of regression, where cross-validation of the prediction error is a widespread and trusted approach for model selection, there are no tools for PCA model selection which reach this level of acceptance. In this work, we address this challenge and evaluate the utility of the cross-validated ignorance score with both simulated and experimental data sets. Application of this method is based on the interpretation of PCA as a density model, as in probabilistic principal component analysis, and is shown to be a valuable tool to identify an optimal number of principal components.

stat.AP↗

arXiv2018

Big Data Meet Cyber-Physical Systems: A Panoramic Survey

The world is witnessing an unprecedented growth of cyber-physical systems (CPS), which are foreseen to revolutionize our world {via} creating new services and applications in a variety of sectors such as environmental monitoring, mobile-health systems, intelligent transportation systems and so on. The {information and communication technology }(ICT) sector is experiencing a significant growth in { data} traffic, driven by the widespread usage of smartphones, tablets and video streaming, along with the significant growth of sensors deployments that are anticipated in the near future. {It} is expected to outstandingly increase the growth rate of raw sensed data. In this paper, we present the CPS taxonomy {via} providing a broad overview of data collection, storage, access, processing and analysis. Compared with other survey papers, this is the first panoramic survey on big data for CPS, where our objective is to provide a panoramic summary of different CPS aspects. Furthermore, CPS {require} cybersecurity to protect {them} against malicious attacks and unauthorized intrusion, which {become} a challenge with the enormous amount of data that is continuously being generated in the network. {Thus, we also} provide an overview of the different security solutions proposed for CPS big data storage, access and analytics. We also discuss big data meeting green challenges in the contexts of CPS.

cs.LG↗

arXiv2017

Tensor Regression Meets Gaussian Processes

Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention. At the same time, Gaussian processes (GP) are well-studied machine learning models for structure learning. In this paper, we demonstrate interesting connections between the two, especially for multi-way data analysis. We show that low-rank tensor regression is essentially learning a multi-linear kernel in Gaussian processes, and the low-rank assumption translates to the constrained Bayesian inference problem. We prove the oracle inequality and derive the average case learning curve for the equivalent GP model. Our finding implies that low-rank tensor regression, though empirically successful, is highly dependent on the eigenvalues of covariance functions as well as variable correlations.

cs.LG↗

arXiv2015

Cellular automaton model simulating spatiotemporal patterns, phase transitions and evolution concavity in traffic flow

This paper firstly show that a recent model (Tian et al., Transpn. Res. B 71, 138-157, 2015) is not able to well replicate the evolution concavity in traffic flow, i.e. the standard deviation of vehicles increases in a concave/linear way along the platoon. Then we propose an improved model by introducing the safe speed, the logistic function of the randomization probability, and small randomization deceleration for low-speed vehicles into the model. Simulations show that the improved model can well reproduce the metastable states, the spatiotemporal patterns, the phase transition behaviors of traffic flow, and the evolution concavity of traffic oscillations. Validating results show that the empirical time series of traffic speed obtained from Floating Car Data can be well simulated as well.

nlin.CG↗

arXiv2005

Could the 47 UMa Planetary System be a Second Solar System: predicting the Earth-like planets

(Abridged)We numerically investigated the dynamical architecture of 47 UMa with the planetary configuration of the best-fit orbital solutions by Fischer et al. We systematically studied the existence of Earth-like planets in the region 0.05 AU $\leq a \leq 2.0$ AU for 47 UMa with numerical simulations, and we also explored the packed planetary geometry and Trojan planets in the system. In the simulations, we found that "hot Earths" at 0.05 AU $\leq a < $ 0.4 AU can dynamically survive at least for 1 Myr. The Earth-like planets can eventually remain in the system for 10 Myr in areas involved in the mean motion resonances (MMR) (e.g., 3:2 MMR) with the inner companion. Moreover, we showed that the 2:1 and 3:1 resonances are on the fringe of stability, while the 5:2 MMR is unstable. Additionally, the 2:1 MMR marks out a remarkable boundary between chaotic and regular motions, inside, most of the orbits can survive, outside, they are mostly lost in the orbital evolution. In a dynamical sense, the most likely candidate for habitable environment is Earth-like planets with orbits in the ranges 0.8 AU $\leq a < 1.0$ AU and 1.0 AU $ < a < 1.30$ AU (except several unstable cases) with relatively low eccentricities. The Trojan planets with low eccentricities and inclinations can secularly last at the triangular equilibrium points of two massive planets. Hence, the 47 UMa planetary system may be a close analog to our solar system.

astro-ph↗

arXiv2005

Constraint on intermediate-range gravity from earth-satellite and lunar orbiter measurements, and lunar laser ranging

In the experimental tests of gravity, there have been considerable interests in the possibility of intermediate-range gravity. In this paper, we use the earth-satellite measurement of earth gravity, the lunar orbiter measurement of lunar gravity, and lunar laser ranging measurement to constrain the intermediate-range gravity from lambda=1.2*10^{7}m - 3.8*10^{8}m. The limits for this range are alpha=10^{-8}-5*10^{-8}, which improve previous limits by about one order of magnitude in the range lambda=1.2*10^{7}m-3.8*10^{8}m.

gr-qc↗

arXiv2004

The Librating Companions in HD 37124, HD 12661, HD 82943, 47 Uma and GJ 876: Alignment or Antialignment?

We investigated the apsidal motion for the multi-planet systems. In the simulations, we found that the two planets of HD 37124, HD 12661, 47 Uma and HD 82943 separately undergo apsidal alignment or antialignment. But the companions of GJ 876 and $\upsilon$ And are only in apsidal lock about $0^{\circ}$. Moreover, we obtained the criteria with Laplace-Lagrange secular theory to discern whether a pair of planets for a certain system are in libration or circulation.

astro-ph↗

arXiv2004

The Stability Analysis of the Extrasolar Planetary Systems

To date, more than 100 giant Jupiter-like planets have been discovered in Doppler surveys of solar-type stars. In this paper, we perform simulations to investigate three systems: GJ 876, HD 82943 and 55 Cnc. The former two systems both have a pair of planets in the 2:1 Mean Motion Resonance (MMR), while the inner two companions of the later is close to 3:1 MMR. By integrating hundreds of the planetary orbits of three systems for million years, we find that for GJ 876 and HD 82943, the critical argument $λ_{1} - 2λ_{2} + \varpi_{1}$ and $λ_{1} - 2λ_{2} + \varpi_{2}$ librate about $0^{\circ}$ or $180^{\circ}$, indicating 2:1 MMR can play an important role in stabilizing the motion of the planets so that they are protected from frequent close encounters. As for 55 Cnc, we further show the three resonant arguments for 3:1 MMR execute librations for millions of years respectively, which reveals the evidence of the resonance for this system. Additionally, we should emphasize another vital mechanism is the apsidal phase-locking between a couple of planets for a certain system. For GJ 876 and HD 82943, we discover the relative apsidal longitudes $\varpi_{1} - \varpi_{2}$ move about $0^{\circ}$ or $180^{\circ}$, respectively; but for 55 Cnc, we find that there exists an asymmetric apsidal libration between two inner planets. Finally, we made a brief discussion about the Habitable Zones in the exoplanetary systems.

astro-ph↗