arXiv subjects

Yang Xiao

Publications and source records attributed to Yang Xiao.

270 records · Page 15Linked to original sources

arXiv2020

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) is proposed as a novel 3D motion representation. With 3D space voxelization, the key idea of 3DV is to encode 3D motion information within depth video into a regular voxel set (i.e., 3DV) compactly, via temporal rank pooling. Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly. 3DV is then abstracted as a point set and input into PointNet++ for 3D action recognition, in the end-to-end learning way. The intuition for transferring 3DV into the point set form is that, PointNet++ is lightweight and effective for deep feature learning towards point set. Since 3DV may lose appearance clue, a multi-stream 3D action recognition manner is also proposed to learn motion and appearance feature jointly. To extract richer temporal order information of actions, we also divide the depth video into temporal splits and encode this procedure in 3DV integrally. The extensive experiments on 4 well-established benchmark datasets demonstrate the superiority of our proposition. Impressively, we acquire the accuracy of 82.4% and 93.5% on NTU RGB+D 120 [13] with the cross-subject and crosssetup test setting respectively. 3DV's code is available at https://github.com/3huo/3DV-Action.

cs.CV↗

arXiv2020

Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

We propose a meta-learning approach that learns from multiple tasks in a transductive setting, by leveraging the unlabeled query set in addition to the support set to generate a more powerful model for each task. To develop our framework, we revisit the empirical Bayes formulation for multi-task learning. The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task. We derive a novel amortized variational inference that couples all the variational posteriors via a meta-model, which consists of a synthetic gradient network and an initialization network. Each variational posterior is derived from synthetic gradient descent to approximate the true posterior on the query set, although where we do not have access to the true gradient. Our results on the Mini-ImageNet and CIFAR-FS benchmarks for episodic few-shot classification outperform previous state-of-the-art methods. Besides, we conduct two zero-shot learning experiments to further explore the potential of the synthetic gradient.

cs.LG↗

arXiv2020

Towards Cognitive Routing based on Deep Reinforcement Learning

Routing is one of the key functions for stable operation of network infrastructure. Nowadays, the rapid growth of network traffic volume and changing of service requirements call for more intelligent routing methods than before. Towards this end, we propose a definition of cognitive routing and an implementation approach based on Deep Reinforcement Learning (DRL). To facilitate the research of DRL-based cognitive routing, we introduce a simulator named RL4Net for DRL-based routing algorithm development and simulation. Then, we design and implement a DDPG-based routing algorithm. The simulation results on an example network topology show that the DDPG-based routing algorithm achieves better performance than OSPF and random weight algorithms. It demonstrate the preliminary feasibility and potential advantage of cognitive routing for future network.

cs.NI↗

arXiv2020

A Survey of Distributed Consensus Protocols for Blockchain Networks

Since the inception of Bitcoin, cryptocurrencies and the underlying blockchain technology have attracted an increasing interest from both academia and industry. Among various core components, consensus protocol is the defining technology behind the security and performance of blockchain. From incremental modifications of Nakamoto consensus protocol to innovative alternative consensus mechanisms, many consensus protocols have been proposed to improve the performance of the blockchain network itself or to accommodate other specific application needs. In this survey, we present a comprehensive review and analysis on the state-of-the-art blockchain consensus protocols. To facilitate the discussion of our analysis, we first introduce the key definitions and relevant results in the classic theory of fault tolerance which help to lay the foundation for further discussion. We identify five core components of a blockchain consensus protocol, namely, block proposal, block validation, information propagation, block finalization, and incentive mechanism. A wide spectrum of blockchain consensus protocols are then carefully reviewed accompanied by algorithmic abstractions and vulnerability analyses. The surveyed consensus protocols are analyzed using the five-component framework and compared with respect to different performance metrics. These analyses and comparisons provide us new insights in the fundamental differences of various proposals in terms of their suitable application scenarios, key assumptions, expected fault tolerance, scalability, drawbacks and trade-offs. We believe this survey will provide blockchain developers and researchers a comprehensive view on the state-of-the-art consensus protocols and facilitate the process of designing future protocols.

cs.CR↗

arXiv2019

Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices

Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc. Although numerous of efforts have already been paid, most of them focus on addressing the eyeblink detection problem under the constrained indoor conditions with the relative consistent subject and environment setup. Nevertheless, towards the practical applications eyeblink detection in the wild is more required, and of greater challenges. However, to our knowledge this has not been well studied before. In this paper, we shed the light to this research topic. A labelled eyeblink in the wild dataset (i.e., HUST-LEBW) of 673 eyeblink video samples (i.e., 381 positives, and 292 negatives) is first established by us. These samples are captured from the unconstrained movies, with the dramatic variation on human attribute, human pose, illumination condition, imaging configuration, etc. Then, we formulate eyeblink detection task as a spatial-temporal pattern recognition problem. After locating and tracking human eye using SeetaFace engine and KCF tracker respectively, a modified LSTM model able to capture the multi-scale temporal information is proposed to execute eyeblink verification. A feature extraction approach that reveals appearance and motion characteristics simultaneously is also proposed. The experiments on HUST-LEBW reveal the superiority and efficiency of our approach. It also verifies that, the existing eyeblink detection methods cannot achieve satisfactory performance in the wild.

cs.CV↗

arXiv2019

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed. Within A2J, anchor points able to capture global-local spatial context information are densely set on depth image as local regressors for the joints. They contribute to predict the positions of the joints in ensemble way to enhance generalization ability. The proposed 3D articulated pose estimation paradigm is different from the state-of-the-art encoder-decoder based FCN, 3D CNN and point-set based manners. To discover informative anchor points towards certain joint, anchor proposal procedure is also proposed for A2J. Meanwhile 2D CNN (i.e., ResNet-50) is used as backbone network to drive A2J, without using time-consuming 3D convolutional or deconvolutional layers. The experiments on 3 hand datasets and 2 body datasets verify A2J's superiority. Meanwhile, A2J is of high running speed around 100 FPS on single NVIDIA 1080Ti GPU.

cs.CV↗

arXiv2019

Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose. We believe this is a crucial step to design robotic systems that can interact with new objects in the wild not belonging to a predefined category. Our main insight is to dynamically condition pose estimation with a representation of the 3D shape of the target object. More precisely, we train a Convolutional Neural Network that takes as input both a test image and a 3D model, and outputs the relative 3D pose of the object in the input image with respect to the 3D model. We demonstrate that our method boosts performances for supervised category pose estimation on standard benchmarks, namely Pascal3D+, ObjectNet3D and Pix3D, on which we provide results superior to the state of the art. More importantly, we show that our network trained on everyday man-made objects from ShapeNet generalizes without any additional training to completely new types of 3D objects by providing results on the LINEMOD dataset as well as on natural entities such as animals from ImageNet.

cs.CV↗

arXiv2019

Comparative evaluation of 2D feature correspondence selection algorithms

Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks. Various 2D (image) correspondence selection algorithms have been presented with decades of progress. Unfortunately, the lack of an in-depth evaluation makes it difficult for developers to choose a proper algorithm given a specific application. This paper fills this gap by evaluating eight 2D correspondence selection algorithms ranging from classical methods to the most recent ones on four standard datasets. The diversity of experimental datasets brings various nuisances including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multi-structures for comprehensive test. To further create different distributions of initial matches, a set of combinations of detector and descriptor is also taken into consideration. We measure the quality of a correspondence selection algorithm from four perspectives, i.e., precision, recall, F-measure and efficiency. According to evaluation results, the current advantages and limitations of all considered algorithms are aggregately summarized which could be treated as a "user guide" for the following developers.

cs.CV↗

arXiv2018

Action Recognition for Depth Video using Multi-view Dynamic Images

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow for motion characterization, dynamic imaging exhibits superior efficiency and compactness. Inspired by the success of dynamic imaging in RGB video, this study extends it to the depth domain. To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed. In particular, the raw depth video is densely projected with respect to different virtual imaging viewpoints by rotating the virtual camera within the 3D space. Subsequently, dynamic images are extracted from the obtained multi-view depth videos and multi-view dynamic images are thus constructed from these images. Accordingly, more view-tolerant visual cues can be involved. A novel CNN model is then proposed to perform feature learning on multi-view dynamic images. Particularly, the dynamic images from different views share the same convolutional layers but correspond to different fully connected layers. This is aimed at enhancing the tuning effectiveness on shallow convolutional layers by alleviating the gradient vanishing problem. Moreover, as the spatial occurrence variation of the actions may impair the CNN, an action proposal approach is also put forth. In experiments, the proposed approach can achieve state-of-the-art performance on three challenging datasets.

cs.CV↗

arXiv2018

Magnetic moments of the spin-1/2 singly charmed baryons in covariant baryon chiral perturbation theory

Recent experimental advances have reignited theoretical interests in heavy-flavor hadrons. In this work, we study the magnetic moments of the spin-1/2 singly charmed baryons up to the next-to-leading order in covariant baryon chiral perturbation theory with the extended-on-mass-shell renormalization scheme. The pertinent low energy constants $g_{1-4}$ are fixed with the help of the quark model and the heavy quark spin flavor symmetry, while the remaining $d_2$, $d_3$, $d_5$ and $d_6$ are determined by fitting to the lattice QCD pion-mass dependent data. We study the magnetic moments as a function of $m_π^2$ and compare our results with those obtained in the heavy baryon chiral perturbation theory. We find that the loop corrections induced by the anti-triplet states are dominated by the baryon pole diagram. In addition, we predict the magnetic moments of the spin-1/2 singly charmed baryons and compare them with those of other approaches.

hep-ph↗

arXiv2018

Covariant chiral nucleon-nucleon contact Lagrangian up to order $\mathcal{O}(q^4)$

We adopt a covariant version of the naive dimensional analysis and construct the chiral two-nucleon contact Lagrangian constrained by Lorentz, parity, charge conjugation, hermitian conjugation, and chiral symmetries. We show that at $\mathcal{O}(q^0)$, $\mathcal{O}(q^2)$, $\mathcal{O}(q^4)$, where $q$ denotes a generic small quantity, there are 4, 13, and 23 terms, respectively. We find that by performing $1/m_N$ expansions, the covariant Lagrangian reduces to the conventional non-relativistic one, which includes 2, 7, and 15 terms at each corresponding order.

nucl-th↗

arXiv2018

Combinatorics of $k$-Farey graphs

With an eye towards studying curve systems on low-complexity surfaces, we introduce and analyze the $k$-Farey graphs $\mathcal{F}_k$ and $\mathcal{F}_{\leqslant k}$, two natural variants of the Farey graph in which we relax the edge condition to indicate intersection number $=k$ or $\le k$, respectively. The former, $\mathcal{F}_k$, is disconnected when $k>1$. In fact, we find that the number of connected components is infinite if and only if $k$ is not a prime power. Moreover, we find that each component of $\mathcal{F}_k$ is an infinite-valence tree whenever $k$ is even, and $\mathrm{Aut}(\mathcal{F}_k)$ is uncountable for $k>1$. As for $\mathcal{F}_{\leqslant k}$, Agol obtained an upper bound of $1+\min\{p:p\text{ is a prime}>k\}$ for both chromatic and clique numbers, and observed that this is an equality when $k$ is either one or two less than a prime. We add to this list the values of $k$ that are three less than a prime equivalent to $11\ (\mathrm{mod}\ 12)$, and we show computer-assisted computations of many values of $k$ for which equality fails.

math.GT↗

arXiv2018

Magnetic moments of the spin-1/2 doubly charmed baryons in covariant baryon chiral perturbation theory

Inspired by the recent discovery of the $Ξ_{cc}^{++}$ by the LHCb Collaboration, we study the magnetic moments of the spin-1/2 doubly charmed baryons up to the next-to-leading order in covariant baryon chiral perturbation theory with the extended-on-mass-shell renormalization scheme. There are three low energy constants at this order, $a_1$, $a_2$ and $g_a$. The latest lattice QCD simulations allow us to fix a combination of $a_1$ and $a_2$, while the axial-vector coupling $g_a$ can be determined in three different ways, either by fitting to the lattice QCD data, or by the quark model, or by the heavy antiquark diquark symmetry. The magnetic moments of the spin-1/2 doubly charmed baryons $Ξ^d_{cc}$ and $Ξ^s_{cc}$ can then be predicted. We compare our results with those obtained in the heavy baryon chiral perturbation theory and other approaches, and point out some inconsistencies between the lattice QCD simulations and the quark model.

hep-ph↗

arXiv2018

Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification

Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To address this, most of the state-of-the-art approaches are proposed based on deep convolutional neural network (CNN), being leveraged by its strong feature learning power and classification boundary fitting capacity. Although the vital role towards person re-identification, how to build effective CNN baseline model has not been well studied yet. To answer this open question, we propose 3 good practices in this paper from the perspectives of adjusting CNN architecture and training procedure. In particular, they are adding batch normalization after the global pooling layer, executing identity categorization directly using only one fully-connected, and using Adam as optimizer. The extensive experiments on 3 widely-used benchmark datasets demonstrate that, our propositions essentially facilitate the CNN baseline model to achieve the state-of-the-art performance without any other high-level domain knowledge or low-level technical trick.

cs.CV↗

arXiv2018

Performance Evaluation of 3D Correspondence Grouping Algorithms

This paper presents a thorough evaluation of several widely-used 3D correspondence grouping algorithms, motived by their significance in vision tasks relying on correct feature correspondences. A good correspondence grouping algorithm is desired to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall. Towards this rule, we deploy the experiments on three benchmarks respectively addressing shape retrieval, 3D object recognition and point cloud registration scenarios. The variety in application context brings a rich category of nuisances including noise, varying point densities, clutter, occlusion and partial overlaps. It also results to different ratios of inliers and correspondence distributions for comprehensive evaluation. Based on the quantitative outcomes, we give a summarization of the merits/demerits of the evaluated algorithms from both performance and efficiency perspectives.

cs.CV↗

arXiv2018

Octet baryon magnetic moments at next-to-next-to-leading order in covariant chiral perturbation theory

We calculate the octet baryon magnetic moments in covariant baryon chiral perturbation theory with the extended-on-mass-shell renormalization scheme up to next-to-next-to-leading order. At this order, there are nine low-energy constants, which cannot be uniquely determined by the seven experimental data alone. We propose two strategies to circumvent this problem. First, we assume that chiral perturbation theory has a certain convergence rate and use this as one additional constraint to fix the low-energy constants by fitting to the experimental data. Second, we fit to lattice QCD simulations to determine the low-energy constants. We then compare the resulting predictions of the light and strange quark mass dependence of the octet baryon magnetic moments by the three mostly studied formulations of baryon chiral perturbation theory, namely, the extended-on-mass-shell, the infrared, and the heavy baryon approach. It is shown that once more precise lattice data become available, one will learn more about the convergence pattern of baryon chiral perturbation theory.

hep-ph↗

arXiv2017

TasselNet: Counting maize tassels in the wild via local counts regression network

Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations. This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment.

cs.CV↗

arXiv2015

Non-archimedean connected Julia sets with branching

We construct the first examples of rational functions defined over a non-archimedean field with certain dynamical properties. In particular, we find such functions whose Julia sets, in the Berkovich projective line, are connected but not contained in a line segment. We also show how to compute the measure-theoretic and topological entropy of such maps. In particular, we show for some of our examples that the measure-theoretic entropy is strictly smaller than the topological entropy, thus answering a question of Favre and Rivera-Letelier.

math.DS↗