arXiv subjects

Yan Lu

Publications and source records attributed to Yan Lu.

At least 253 records · Page 14Linked to original sources

arXiv2020

Weakly-supervised Temporal Action Localization by Uncertainty Modeling

Weakly-supervised temporal action localization aims to learn detecting temporal intervals of action classes with only video-level labels. To this end, it is crucial to separate frames of action classes from the background frames (i.e., frames not belonging to any action classes). In this paper, we present a new perspective on background frames where they are modeled as out-of-distribution samples regarding their inconsistency. Then, background frames can be detected by estimating the probability of each frame being out-of-distribution, known as uncertainty, but it is infeasible to directly learn uncertainty without frame-level labels. To realize the uncertainty learning in the weakly-supervised setting, we leverage the multiple instance learning formulation. Moreover, we further introduce a background entropy loss to better discriminate background frames by encouraging their in-distribution (action) probabilities to be uniformly distributed over all action classes. Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles. We demonstrate that our model significantly outperforms state-of-the-art methods on the benchmarks, THUMOS'14 and ActivityNet (1.2 & 1.3). Our code is available at https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling.

cs.CV↗

arXiv2020

M Subdwarf Research. II. Atmospheric Parameters and Kinematics

Applying the revised M subdwarf classification criteria discussed in Paper I to LAMOST DR7, combining the M subdwarf sample from Savcheva et al, a new M subdwarf sample was constructed for further study. The atmospheric parameters for each object were derived fitting with the PHOENIX grid, combining with Gaia DR2, the relationship between the gravity and metallicity were explored according to the locus both in the color-absolute magnitude diagram and the reduced proper motion diagram. Objects that have both the largest gravity and the lowest metallicity are located away from the main-sequence cloud and may be considered as the intrinsic M subdwarfs, which can be classified as luminosity class VI. Another group of objects whose spectra show typical M subdwarf characters have lower gravity and relatively moderate metal deficiency and occupy part of the ordinary M dwarf region in both diagrams. The Galactic U , V , W space velocity components and their dispersion show that the local Galactic halo population sampled in the solar neighborhood is represented by objects of high gravity and an inconspicuous bimodal metallicity distribution, with a fraction of prograde orbits. The other M subdwarfs seem to partly belong to the thick disk component with a significant fraction of thin disk moderately metal-poor objects intricately mixed with them. However, the selection effects, especially the favored anti-center direction of investigation in the LAMOST sub-sample, but also contamination by multiplicity and parameter coupling could play important roles and need to be further investigated.

astro-ph.SR↗

arXiv2020

Double Dirac Cones and Topologically Non-Trivial Phonons for Continuous, Square Symmetric (C$_{4v}$ and C$_{2v}$) Unit Cells

Because phononic topological insulators have primarily been studied in discrete, graphene-like structures with C$_{6}$ or C$_{3}$ hexagonal symmetry, an open question is how to systematically achieve double Dirac cones and topologically non-trivial structures using continuous, non-hexagonal unit cells. Here, we address this challenge by presenting a novel computational methodology for the inverse design of continuous two-dimensional square phononic metamaterials exhibiting C$_{4v}$ and C$_{2v}$ symmetry. This leads to the systematic design of square unit cell topologies exhibiting a double Dirac degeneracy, which enables topologically-protected interface propagation based on the quantum spin Hall effect (QSHE). Numerical simulations prove that helical edge states emerge at the interface between two topologically distinct square phononic metamaterials, which opens the possibility of QSHE-based pseudospin-dependent transport beyond hexagonal lattices.

cond-mat.mes-hall↗

arXiv2020

Weakly Supervised 3D Object Detection from Point Clouds

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during training, while these annotations could be expensive to obtain and only accessible in limited scenarios. Weakly supervised learning is a promising approach to reducing the annotation requirement, but existing weakly supervised object detectors are mostly for 2D detection rather than 3D. In this work, we propose VS3D, a framework for weakly supervised 3D object detection from point clouds without using any ground truth 3D bounding box for training. First, we introduce an unsupervised 3D proposal module that generates object proposals by leveraging normalized point cloud densities. Second, we present a cross-modal knowledge distillation strategy, where a convolutional neural network learns to predict the final results from the 3D object proposals by querying a teacher network pretrained on image datasets. Comprehensive experiments on the challenging KITTI dataset demonstrate the superior performance of our VS3D in diverse evaluation settings. The source code and pretrained models are publicly available at https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection.

cs.CV↗

arXiv2020

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression. Unlike the pixel-level depth estimation that needs per-pixel annotations, we propose a novel IDE method that directly predicts the depth of the targeting 3D bounding box's center using sparse supervision. The 3D localization is further achieved by estimating the position in the horizontal and vertical dimensions. Finally, MonoGRNet is jointly learned by optimizing the locations and poses of the 3D bounding boxes in the global context. We demonstrate that MonoGRNet achieves state-of-the-art performance on challenging datasets.

cs.CV↗

arXiv2020

Enhanced Catalytic Activity of Gold@Polydopamine Nanoreactors with Multi-compartment Structure Under NIR Irradiation

Photothermal conversion (PTC) nanostructures have great potential for applications in many fields, and therefore, they have attracted tremendous attention. However, the construction of a PTC nanoreactor with multi-compartment structure to achieve the combination of unique chemical properties and structural feature is still challenging due to the synthetic difficulties. Herein, we designed and synthesized a catalytically active, PTC gold (Au)@polydopamine (PDA) nanoreactor driven by infrared irradiation using assembled PS-b-P2VP nanosphere as soft template. The particles exhibit multi-compartment structure which is revealed by 3D electron tomography characterization technique. They feature permeable shells with tunable shell thickness. Full kinetics for the reduction reaction of 4-nitrophenol has been investigated using these particles as nanoreactors and compared with other reported systems. Notably, a remarkable acceleration of the catalytic reaction upon near-infrared irradiation is demonstrated, which reveals for the first time the importance of the synergistic effect of photothermal conversion and complex inner structure to the kinetics of the catalytic reduction. The ease of synthesis and fresh insights into catalysis will promote a new platform for novel nanoreactor studies.

physics.chem-ph↗

arXiv2020

Cross-modality Person re-identification with Shared-Specific Feature Transfer

Cross-modality person re-identification (cm-ReID) is a challenging but key technology for intelligent video analysis. Existing works mainly focus on learning common representation by embedding different modalities into a same feature space. However, only learning the common characteristics means great information loss, lowering the upper bound of feature distinctiveness. In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance. We model the affinities of different modality samples according to the shared features and then transfer both shared and specific features among and across modalities. We also propose a complementary feature learning strategy including modality adaption, project adversarial learning and reconstruction enhancement to learn discriminative and complementary shared and specific features of each modality, respectively. The entire cm-SSFT algorithm can be trained in an end-to-end manner. We conducted comprehensive experiments to validate the superiority of the overall algorithm and the effectiveness of each component. The proposed algorithm significantly outperforms state-of-the-arts by 22.5% and 19.3% mAP on the two mainstream benchmark datasets SYSU-MM01 and RegDB, respectively.

cs.CV↗

arXiv2020

Scattering under Linear Non Self-Adjoint Operators: Case of in-Plane Elastic Waves

In this paper, we consider the problem of the scattering of in-plane waves at an interface between a homogeneous medium and a metamaterial. The relevant eigenmodes in the two regions are calculated by solving a recently described non self-adjoint eigenvalue problem particularly suited to scattering studies. The method efficiently produces all propagating and evanescent modes consistent with the application of Snell's law and is applicable to very general scattering problems. In a model composite, we elucidate the emergence of a rich spectrum of eigenvalue degeneracies. These degeneracies appear in both the complex and real domains of the wave-vector. However, since this problem is non self-adjoint, these degeneracies generally represent a coalescing of both the eigenvalues and eigenvectors (exceptional points). Through explicit calculations of Poynting vector, we point out an intriguing phenomenon: there always appears to be an abrupt change in the sign of the refraction angle of the wave on two sides of an exceptional point. Furthermore, the presence of these degeneracies, in some cases, hints at fast changes in the scattered field as the incident angle is changed by small amounts. We calculate these scattered fields through a novel application of the Betti-Rayleigh reciprocity theorem. We present several numerical examples showing a rich scattering spectrum. In one particularly intriguing example, we point out wave behavior which may be related to the phenomenon of resonance trapping. We also show that there exists a deep connection between energy flux conservation and the biorthogonality relationship of the non self-adjoint problem. The proof applies to the general class of scattering problems involving elastic waves (under self-adjoint or non self-adjoint operators).

physics.app-ph↗

arXiv2020

Artificial Multiferroics and Enhanced Magnetoelectric Effect in van der Waals Heterostructures

Multiferroic materials with coupled ferroelectric and ferromagnetic properties are important for multifunctional devices due to their potential ability of controlling magnetism via electric field, and vice versa. The recent discoveries of two-dimensional ferromagnetic and ferroelectric materials have ignited tremendous research interest and aroused hope to search for two-dimensional multiferroics. However, intrinsic two-dimensional multiferroic materials and, particularly, those with strong magnetoelectric couplings are still rare to date. In this paper, using first-principles simulations, we propose artificial two-dimensional multiferroics via a van der Waals heterostructure formed by ferromagnetic bilayer chromium triiodide (CrI3) and ferroelectric monolayer Sc2CO2. In addition to the coexistence of ferromagnetism and ferroelectricity, our calculations show that, by switching the electric polarization of Sc2CO2, we can tune the interlayer magnetic couplings of bilayer CrI3 between ferromagnetic and antiferromagnetic states. We further reveal that such a strong magnetoelectric effect is from a dramatic change of the band alignment induced by the strong build-in electric polarization in Sc2CO2 and the subsequent change of the interlayer magnetic coupling of bilayer CrI3. These artificial multiferroics and enhanced magnetoelectric effect give rise to realizing multifunctional nanoelectronics by van der Waals heterostructures.

cond-mat.mes-hall↗

arXiv2020

WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes

Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances of computer vision and machine learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of compute budget, making them incompetent to adapt to time-varying tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy trade-offs, and decompose and schedule tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, showing a 100% tracking coverage with real-time guarantee.

cs.DC↗

arXiv2019

Reinforcement learning for bandwidth estimation and congestion control in real-time communications

Bandwidth estimation and congestion control for real-time communications (i.e., audio and video conferencing) remains a difficult problem, despite many years of research. Achieving high quality of experience (QoE) for end users requires continual updates due to changing network architectures and technologies. In this paper, we apply reinforcement learning for the first time to the problem of real-time communications (RTC), where we seek to optimize user-perceived quality. We present initial proof-of-concept results, where we learn an agent to control sending rate in an RTC system, evaluating using both network simulation and real Internet video calls. We discuss the challenges we observed, particularly in designing realistic reward functions that reflect QoE, and in bridging the gap between the training environment and real-world networks.

cs.NI↗

arXiv2019

On the Properties of Phononic Eigenvalue Problems

In this paper, we consider the operator properties of various phononic eigenvalue problems. We aim to answer some fundamental questions about the eigenvalues and eigenvectors of phononic operators. These include questions about the potential real and complex nature of the eigenvalues, whether the eigenvectors form a complete basis, what are the right orthogonality relationships, and how to create a complete basis when none may exist at the outset. In doing so we present a unified understanding of the properties of the phononic eigenvalues and eigenvectors which would emerge from any numerical method employed to compute such quantities. We show that the phononic problem can be cast into linear eigenvalue forms from which such quantities as frequencies, wavenumbers, and desired components of wavevectors can be directly ascertained without resorting to searches or quadratic eigenvalue problems and that the relevant properties of such quantities can be determined apriori through the analysis of the associated operators. We further show how the Plane Wave Expansion (PWE) method may be extended to solve each of these eigenvalue forms, thus extending the applicability of the PWE method to cases beyond those which have been considered till now. The theoretical discussions are supplemented with supporting numerical calculations. The techniques and results presented here directly apply to wave propagation in other periodic systems such as photonics.

physics.comp-ph↗

arXiv2019

Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing 3D anchors to explicitly construct object-level correspondences between the regions of interest in stereo images, from which the deep neural network learns to detect and triangulate the targeted object in 3D space. We also introduce a cost-efficient channel reweighting strategy that enhances representational features and weakens noisy signals to facilitate the learning process. All of these are flexibly integrated into a solid baseline detector that uses monocular images. We demonstrate that both the monocular baseline and the stereo triangulation learning network outperform the prior state-of-the-arts in 3D object detection and localization on the challenging KITTI dataset.

cs.CV↗

arXiv2019

Relational Knowledge Distillation

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conducted on different tasks show that the proposed method improves educated student models with a significant margin. In particular for metric learning, it allows students to outperform their teachers' performance, achieving the state of the arts on standard benchmark datasets.

cs.CV↗

arXiv2019

Ionic Organic Cage-encapsulating Phase-transferable Metal Clusters

Exploration of metal clusters (MCs) adaptive to both aqueous and oil phases without disturbing their size is promising for a broad scope of applications. The state-of-the-art approach via ligand-binding may perturb MC size due to varied metal-ligand binding strength when shuttling between solvents of different polarity. Herein, we applied physical confinement of a series of small noble MCs (less than 1 nm) inside ionic organic cages (I-Cages), which by means of anion exchange enables reversible transfer of MCs between aqueous and hydrophobic solutions without varying their ultrasmall size. Moreover, the MCs(at)I-Cage hybrid serves as a recyclable, reaction-switchable catalyst featuring high activity in liquid-phase catalysis.

physics.chem-ph↗

arXiv2019

See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image guided by these attention maps, including attention cropping and attention dropping. The proposed WS-DAN improves the classification accuracy in two folds. In the first stage, images can be seen better since more discriminative parts' features will be extracted. In the second stage, attention regions provide accurate location of object, which ensures our model to look at the object closer and further improve the performance. Comprehensive experiments in common fine-grained visual classification datasets show that our WS-DAN surpasses the state-of-the-art methods, which demonstrates its effectiveness.

cs.CV↗

arXiv2019

Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification

For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extracting discriminative local features play a crucial role in accurate category prediction. Existing works either pay attention to limited object parts or train isolated networks for locating and classification. In this paper, we propose Weakly Supervised Bilinear Attention Network (WS-BAN) to solve these issues. It jointly generates a set of attention maps (region-of-interest maps) to indicate the locations of object's parts and extracts sequential part features by Bilinear Attention Pooling (BAP). Besides, we propose attention regularization and attention dropout to weakly supervise the generating process of attention maps. WS-BAN can be trained end-to-end and achieves the state-of-the-art performance on multiple fine-grained classification datasets, including CUB-200-2011, Stanford Car and FGVC-Aircraft, which demonstrated its effectiveness.

cs.CV↗

arXiv2019

On the Emergence of Negative Effective Density and Modulus in 2-phase Phononic Crystals

In this paper we report metamaterial properties including negative and singular effective properties for what would traditionally be considered non locally resonant 2-phase phononic unit cells. The negative effective material properties reported here occur well below the homogenization limit and are, therefore, acceptable descriptions of overall behavior. The material property combinations which make this possible were first revealed by a novel level set based topology optimization process which we describe. The optimization process revealed that a 2-phase unit cell in which one of the phases is simultaneously lighter and stiffer than the other results in dynamic behavior which has all the attendant characteristics of a locally resonant composite including negative effective properties far below the homogenization limit. We investigate this further using the Craig-Bampton decomposition and clarify that these properties emerge through an interplay between the fundamental internal modeshape of the unit cell and a rigid body mode. Through explicit numerical calculations on 1-D, 2-phase unit cells, we show that negative effective properties only appear for the specific material property combination mentioned above. Furthermore, we provide a proof which supports this conclusion. The concept is also shown to hold for 2-D unit cells where we show that an appropriately designed hexagonal unit cell made of 2 material phases exhibits negative effective shear modulus and density in an appropriate frequency regime in which it also exhibits negative refraction. An important conclusion of this paper is that the class of unit cells expected to result in negative properties can be expanded beyond the classic unit cell (three-phase unit cells with an explicit locally resonant phase) to include topologically simpler 2-phase unit cells as well.

physics.app-ph↗