arXiv subjects

Long Zhao

Publications and source records attributed to Long Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2021

Energy spectrum of gravitational waves

The energy spectrum of gravitational waves (GWs), which depicts the energy of GWs per unit volume of space per logarithmic frequency interval normalized to the critical density of the Universe, is a widely used way for quantifying the sensitivity of GW detectors and the strength of GWs, since it has the advantage of having a clear physical meaning. It was found that the energy spectrum of GWs depends on the gauge when the GWs beyond the linear order perturbations are considered. We show that this gauge dependence issue originates from the inappropriate description for the energy of GWs. With the proper description for the energy of GWs, we give a well-defined energy spectrum of GWs, in which the gauge issue disappears naturally.

astro-ph.CO↗

arXiv2021

Scenario Generation of Wind Farm Power for Real-Time System Operation

This work proposes a method of wind farm scenario generation to support real-time optimization tools and presents key findings therein. This work draws upon work from the literature and presents an efficient and scalable method for producing an adequate number of scenarios for a large fleet of wind farms while capturing both spatial and temporal dependencies. The method makes probabilistic forecasts using conditional heteroscedastic regression for each wind farm and time horizon. Past training data is transformed (using the probabilistic forecasting models) into standard normal samples. A Gaussian copula is estimated from the normalized samples and used in real-time to enforce proper spatial and temporal dependencies. The method is evaluated using historical data from MISO and performance within the MISO real-time look-ahead framework is discussed.

stat.AP↗

arXiv2021

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information maximization (CV-MIM) which maximizes mutual information of the same pose performed from different viewpoints in a contrastive learning manner. We further propose two regularization terms to ensure disentanglement and smoothness of the learned representations. The resulting pose representations can be used for cross-view action recognition. To evaluate the power of the learned representations, in addition to the conventional fully-supervised action recognition settings, we introduce a novel task called single-shot cross-view action recognition. This task trains models with actions from only one single viewpoint while models are evaluated on poses captured from all possible viewpoints. We evaluate the learned representations on standard benchmarks for action recognition, and show that (i) CV-MIM performs competitively compared with the state-of-the-art models in the fully-supervised scenarios; (ii) CV-MIM outperforms other competing methods by a large margin in the single-shot cross-view setting; (iii) and the learned representations can significantly boost the performance when reducing the amount of supervised training data. Our code is made publicly available at https://github.com/google-research/google-research/tree/master/poem

cs.CV↗

arXiv2021

SMIL: Multimodal Learning with Severely Missing Modality

A common assumption in multimodal learning is the completeness of training data, i.e., full modalities are available in all training examples. Although there exists research endeavor in developing novel methods to tackle the incompleteness of testing data, e.g., modalities are partially missing in testing examples, few of them can handle incomplete training modalities. The problem becomes even more challenging if considering the case of severely missing, e.g., 90% training examples may have incomplete modalities. For the first time in the literature, this paper formally studies multimodal learning with missing modality in terms of flexibility (missing modalities in training, testing, or both) and efficiency (most training data have incomplete modality). Technically, we propose a new method named SMIL that leverages Bayesian meta-learning in uniformly achieving both objectives. To validate our idea, we conduct a series of experiments on three popular benchmarks: MM-IMDb, CMU-MOSI, and avMNIST. The results prove the state-of-the-art performance of SMIL over existing methods and generative baselines including autoencoders and generative adversarial networks. Our code is available at https://github.com/mengmenm/SMIL.

cs.CV↗

arXiv2021

Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection

False positive is one of the most serious problems brought by agnostic domain shift in domain adaptive pedestrian detection. However, it is impossible to label each box in countless target domains. Therefore, it yields our attention to suppress false positive in each target domain in an unsupervised way. In this paper, we model an object detection task into a ranking task among positive and negative boxes innovatively, and thus transform a false positive suppression problem into a box re-ranking problem elegantly, which makes it feasible to solve without manual annotation. An attached problem during box re-ranking appears that no labeled validation data is available for cherrypicking. Considering we aim to keep the detection of true positive unchanged, we propose box number alignment, a self-supervised evaluation metric, to prevent the optimized model from capacity degeneration. Extensive experiments conducted on cross-domain pedestrian detection datasets have demonstrated the effectiveness of our proposed framework. Furthermore, the extension to two general unsupervised domain adaptive object detection benchmarks also supports our superiority to other state-of-the-arts.

cs.CV↗

arXiv2020

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

Adversarial data augmentation has shown promise for training robust deep neural networks against unforeseen data shifts or corruptions. However, it is difficult to define heuristics to generate effective fictitious target distributions containing "hard" adversarial perturbations that are largely different from the source distribution. In this paper, we propose a novel and effective regularization term for adversarial data augmentation. We theoretically derive it from the information bottleneck principle, which results in a maximum-entropy formulation. Intuitively, this regularization term encourages perturbing the underlying source distribution to enlarge predictive uncertainty of the current model, so that the generated "hard" adversarial perturbations can improve the model robustness during training. Experimental results on three standard benchmarks demonstrate that our method consistently outperforms the existing state of the art by a statistically significant margin.

cs.LG↗

arXiv2020

Wormholes and the Thermodynamic Arrow of Time

In classical thermodynamics, heat cannot spontaneously pass from a colder system to a hotter system, which is called the thermodynamic arrow of time. However, if the initial states are entangled, the direction of the thermodynamic arrow of time may not be guaranteed. Here we take the thermofield double state at $0+1$ dimension as the initial state and assume its gravity duality to be the eternal black hole in AdS$_2$ space. We make the temperature difference between the two sides by changing the Hamiltonian. We turn on proper interaction between the two sides and calculate the changes in energy and entropy. The energy transfer, as well as the thermodynamic arrow of time, are mainly determined by the competition between two channels: thermal diffusion and anomalous heat flow. The former is not related to the wormhole and obeys the thermodynamic arrow of time; the latter is related to the wormhole and reverses the thermodynamic arrow of time, i.e. transferring energy from the colder side to the hotter side at the cost of entanglement consumption. Finally, we find that the thermal diffusion wins the competition, and the whole thermodynamic arrow of time has not been reversed.

hep-th↗

arXiv2020

Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine

Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries. In this paper, we explore a vector space search framework for document retrieval. Specifically, we trained a deep semantic matching model so that each query and document can be encoded as a low dimensional embedding. Our model was trained based on BERT architecture. We deployed a fast k-nearest-neighbor index service for online serving. Both offline and online metrics demonstrate that our method improved retrieval performance and search quality considerably, particularly for tail

cs.IR↗

arXiv2020

Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge

Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist in both modalities. However, accessing the data from superior modalities may not always be feasible. For example, in the case of 3D hand pose estimation, depth maps, point clouds, or stereo images usually capture better hand structures than RGB images, but most of them are expensive to be collected. In this paper, we propose a novel scheme to train the Student in a Target dataset where the Teacher is unavailable. Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student. We name our method "Cross-Modal Knowledge Generalization" and demonstrate that our scheme results in competitive performance for 3D hand pose estimation on standard benchmark datasets.

cs.CV↗

arXiv2020

Learning to Learn Single Domain Generalization

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named adversarial domain augmentation to solve this Out-of-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint. Detailed theoretical analysis is provided to testify our formulation, while extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.

cs.CV↗

arXiv2020

Semantic Graph Convolutional Networks for 3D Human Pose Regression

In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.

cs.CV↗

arXiv2020

Twin-Timescale Radio Resource Management for Ultra-Reliable and Low-Latency Vehicular Networks

To efficiently support safety-related vehicular applications, the ultra-reliable and low-latency communication (URLLC) concept has become an indispensable component of vehicular networks (VNETs). Due to the high mobility of VNETs, exchanging near-instantaneous channel state information (CSI) and making reliable resource allocation decisions based on such short-term CSI evaluations are not practical. In this paper, we consider the downlink of a vehicle-to-infrastructure (V2I) system conceived for URLLC based on idealized perfect and realistic imperfect CSI. By exploiting the benefits of the massive MIMO concept, a two-stage radio resource allocation problem is formulated based on a novel twin-timescale perspective for avoiding the frequent exchange of near-instantaneous CSI. Specifically, based on the prevalent road-traffic density, Stage 1 is constructed for minimizing the worst-case transmission latency on a long-term timescale. In Stage 2, the base station allocates the total power at a short-term timescale according to the large-scale fading CSI encountered for minimizing the maximum transmission latency across all vehicular users. Then, a primary algorithm and a secondary algorithm are conceived for our V2I URLLC system to find the optimal solution of the twin-timescale resource allocation problem, with special emphasis on the complexity imposed. Finally, our simulation results show that the proposed resource allocation scheme significantly reduces the maximum transmission latency, and it is not sensitive to the fluctuation of road-traffic density.

cs.IT↗

arXiv2019

Optimal Power Flow in Hybrid AC and Multi-terminal HVDC Networks with Offshore Wind Farm Integration Based on Semidefinite Programming

Multi-terminal high voltage direct current (MTHVDC) technology is a promising technology for the offshore wind farm integration, which requires the new control and operation scheme. Therefore, the optimal power flow problem for this system is important to achieve the optimal economic operation. In this paper, convex relaxation model based on semidefinite programming for the MT-HVDC system considering DC/DC converters is proposed to solve the optimal power flow problem. A hybrid AC and MT-HVDC system for offshore wind farm integration is used for the test. The simulation results validate the effectiveness of the proposed model and guarantee that the global optimum solution is achieved.

eess.SY↗

arXiv2019

Rethinking Kernel Methods for Node Representation Learning on Graphs

Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification. However, the use of kernel methods for node classification, which is a related problem to graph representation learning, is still ill-posed and the state-of-the-art methods are heavily based on heuristics. Here, we present a novel theoretical kernel-based framework for node classification that can bridge the gap between these two representation learning problems on graphs. Our approach is motivated by graph kernel methodology but extended to learn the node representations capturing the structural information in a graph. We theoretically show that our formulation is as powerful as any positive semidefinite kernels. To efficiently learn the kernel, we propose a novel mechanism for node feature aggregation and a data-driven similarity metric employed during the training phase. More importantly, our framework is flexible and complementary to other graph-based deep learning models, e.g., Graph Convolutional Networks (GCNs). We empirically evaluate our approach on a number of standard node classification benchmarks, and demonstrate that our model sets the new state of the art.

cs.LG↗

arXiv2019

Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention

We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand skeleton, where the node features and edges are then automatically learned via a self-attention mechanism that performs in both spatial and temporal domains. We further propose to leverage the spatial-temporal cues of joint positions to guarantee robust recognition in challenging conditions. In addition, a novel spatial-temporal mask is applied to significantly cut down the computational cost by 99%. We carry out extensive experiments on benchmarks (DHG-14/28 and SHREC'17) and prove the superior performance of our method compared with the state-of-the-art methods. The source code can be found at https://github.com/yuxiaochen1103/DG-STA.

cs.CV↗

arXiv2019

A Driving Intention Prediction Method Based on Hidden Markov Model for Autonomous Driving

In a mixed-traffic scenario where both autonomous vehicles and human-driving vehicles exist, a timely prediction of driving intentions of nearby human-driving vehicles is essential for the safe and efficient driving of an autonomous vehicle. In this paper, a driving intention prediction method based on Hidden Markov Model (HMM) is proposed for autonomous vehicles. HMMs representing different driving intentions are trained and tested with field collected data from a flyover. When training the models, either discrete or continuous characterization of the mobility features of vehicles is applied. Experimental results show that the HMMs trained with the continuous characterization of mobility features can give a higher prediction accuracy when they are used for predicting driving intentions. Moreover, when the surrounding traffic of the vehicle is taken into account, the performances of the proposed prediction method are further improved.

cs.LG↗

arXiv2019

Short-term Road Traffic Prediction based on Deep Cluster at Large-scale Networks

Short-term road traffic prediction (STTP) is one of the most important modules in Intelligent Transportation Systems (ITS). However, network-level STTP still remains challenging due to the difficulties both in modeling the diverse traffic patterns and tacking high-dimensional time series with low latency. Therefore, a framework combining with a deep clustering (DeepCluster) module is developed for STTP at largescale networks in this paper. The DeepCluster module is proposed to supervise the representation learning in a visualized way from the large unlabeled dataset. More specifically, to fully exploit the traffic periodicity, the raw series is first split into a number of sub-series for triplets generation. The convolutional neural networks (CNNs) with triplet loss are utilized to extract the features of shape by transferring the series into visual images. The shape-based representations are then used for road segments clustering. Thereafter, motivated by the fact that the road segments in a group have similar patterns, a model sharing strategy is further proposed to build recurrent NNs (RNNs)-based predictions through a group-based model (GM), instead of individual-based model (IM) in which one model are built for one road exclusively. Our framework can not only significantly reduce the number of models and cost, but also increase the number of training data and the diversity of samples. In the end, we evaluate the proposed framework over the network of Liuli Bridge in Beijing. Experimental results show that the DeepCluster can effectively cluster the road segments and GM can achieve comparable performance against the IM with less number of models.

cs.LG↗

arXiv2019

Cooperative V2X for High Definition Map Transmission Based on Vehicle Mobility

High-definition (HD) map transmission is considered as a key technology for automatic driving, which enables vehicles to obtain the precise road and surrounding environment information for further localization and navigation. Guaranteeing the huge requirement of HD map data, the objective of this paper is to reduce the power consumption of vehicular networks. By leveraging the mobile rule of vehicles, a collaborative vehicle to everything (V2X) transmission scheme is proposed for the HD map transmission. Numerical results indicate that the proposed scheme can satisfy the transmission rate requirement of HD map with low power consumption.

eess.SP↗