arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,153 records · Page 64Linked to original sources

arXiv2022

New graph-based multi-sample tests for high-dimensional and non-Euclidean data

Testing the equality in distributions of multiple samples is a common task in many fields. However, this problem for high-dimensional or non-Euclidean data has not been well explored. In this paper, we propose new nonparametric tests based on a similarity graph constructed on the pooled observations from multiple samples, and make use of both within-sample edges and between-sample edges, a straightforward but yet not explored idea. The new tests exhibit substantial power improvements over existing tests for a wide range of alternatives. We also study the asymptotic distributions of the test statistics, offering easy off-the-shelf tools for large datasets. The new tests are illustrated through an analysis of the age image dataset.

stat.ME↗

arXiv2022

What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions

We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions. Differently from previous Transformer-based HOI approaches, which mostly focus at improving the design of the decoder outputs for the final detection, SSRT introduces two new modules to help select the most relevant object-action pairs within an image and refine the queries' representation using rich semantic and spatial features. These enhancements lead to state-of-the-art results on the two most popular HOI benchmarks: V-COCO and HICO-DET.

cs.CV↗

arXiv2022

Heteromoiré Engineering on Magnetic Bloch Transport in Twisted Graphene Superlattices

Localized electrons subject to applied magnetic fields can restart to propagate freely through the lattice in delocalized magnetic Bloch states (MBSs) when the lattice periodicity is commensurate with the magnetic length. Twisted graphene superlattices with moiré wavelength tunability enable experimental access to the unique delocalization in a controllable fashion. Here we report the observation and characterization of high-temperature Brown-Zak (BZ) oscillations which come in two types, 1/B and B periodicity, originating from the generation of integer and fractional MBSs, in the twisted bilayer and trilayer graphene superlattices, respectively. Coexisting periodic-in-1/B oscillations assigned to different moiré wavelengths, are dramatically observed in small-angle twisted bilayer graphene, which may arise from angle-disorder-induced in-plane heteromoiré superlattices. Moreover, the vertical stacking of heteromoiré supercells in double-twisted trilayer graphene results in a mega-sized superlattice. The exotic superlattice contributes to the periodic-in-B oscillation and dominates the magnetic Bloch transport.

cond-mat.mes-hall↗

arXiv2022

Coordinate-ordering-free Upper Bounds for Linear Insertion-Deletion Codes

The insertion-deletion codes were motivated to correct the synchronization errors. In this paper we prove several coordinate-ordering-free upper bounds on the insdel distances of linear codes, which are based on the generalized Hamming weights and the formation of minimum Hamming weight codewords. Our bounds are stronger than some previous known bounds. We apply these upper bounds to some cyclic codes and one algebraic-geometric code with any rearrangement of coordinate positions. Some strong upper bounds on the insdel distances of Reed-Muller codes with special coordinate-ordering are also given.

cs.IT↗

arXiv2022

The influence of Aharonov-Casher effect on the generalized Dirac oscillator in the cosmic string space-time

In this manuscript, we investigate the influence of the Aharonov-Casher effect on the generalized Dirac oscillator containing the Coulomb-type potential function related to a relativistic neutral particle having a permanent magnetic dipole moment interacting with the external electromagnetic fields in (1+2)-dimensional cosmic string space-time. The eigenfunctions and energy eigenvalues of such a Dirac oscillator are derived by using the Nikifornov-Uvarov method. We indicate that implementing the scenario gives the relativistic modified exact analytical solutions. In this way, we can see that the degeneracy of the relevant relativistic energy eigenvalues is broken by depending on the Coulomb strength parameter under the influence of the curvature effect and the Aharonov-Casher effect.

quant-ph↗

arXiv2022

TubeR: Tubelet Transformer for Video Action Detection

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.

cs.CV↗

arXiv2022

Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation

Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentally a correspondence-based optimization problem, but previous learning-based methods mainly rely on predefined depth hypotheses to build correspondence as the cost volume and implicitly regularize it to fit depth prediction, deviating from the essence of iterative optimization based on stereo correspondence. Thus, they suffer unsatisfactory precision and generalization capability. In this paper, we are the first to explore more general image correlations to establish correspondences dynamically for depth estimation. We design a novel iterative multi-view depth estimation framework mimicking the optimization process, which consists of 1) a correlation volume construction module that models the pixel similarity between a reference image and source images as all-to-all correlations; 2) a flow-based depth initialization module that estimates the depth from the 2D optical flow; 3) a novel correlation-guided depth refinement module that reprojects points in different views to effectively fetch relevant correlations for further fusion and integrate the fused correlation for iterative depth update. Without predefined depth hypotheses, the fused correlations establish multi-view correspondence in an efficient way and guide the depth refinement heuristically. We conduct sufficient experiments on ScanNet, DeMoN, ETH3D, and 7Scenes to demonstrate the superiority of our method on multi-view depth estimation and its best generalization ability.

cs.CV↗

arXiv2022

Thermodynamics of the Bardeen Black Hole with quintessence matter on the EGUP framework

In this paper, we have used the extended generalized uncertainty principle to investigate the thermodynamics of the Bardeen Black Hole with quintessence matter on the EGUP framework. We started with a brief perusal of the Extended generalized uncertainty principle. Subsequently, the EGUP-modified Hawking temperature, heat capacity, and entropy functions of the Bardeen Black Hole are obtained, which show that the modified uncertainty principles and normalization factor restrict the lower bound value of horizon radius to affect the Hawking temperature. Moreover, we compare and discuss the findings within the generalized uncertainty principle (GUP) and extended uncertainty principle (EUP). In addition, we examine the equation of state associated with the pressure and the volume.

gr-qc↗

arXiv2022

WKB approximation under Killingbeck potential and its application to double heavy meson mass spectrum

As we all known that non-relativistic or semi-relativistic constituent quark models can describe a large number of the meson sand baryon properties with surprising accuracy. In this work, we studied Killingbeck potential by using WKB approximation in the constituent quark model. The implicit approximate solution of the energy eigenvalue of the Schrödinger equation is obtained by using appropriate quantization conditions. Under the Killingbeck potential with the WKB approximation, we studied the spectra of double heavy mesons and predict the masses of high excited states in $c\bar{c}$, $b\bar{b}$ and $b\bar{c}$ families. Finally, we discuss the application scope of double heavy mesons in Killingbeck potential.

hep-ph↗

arXiv2022

On The Low Speed Limits of Lorentz's Transformation

This article contains a digest of the theory of electromagnetism and a review of the transformation between inertial frames, especially under low speed limits. The covariant nature of the Maxwell's equations is explained using the conventional language. We show that even under low speed limits, the relativistic effects should not be neglected to get a self-consistent theory of the electromagnetic fields, unless the intrinsic dynamics of these fields has been omitted completely. The quasi-static limits, where the relativistic effects can be partly neglected are also reviewed, to clarify some common misunderstandings and imprecise use of the theory in presence of moving media and other related situations. The discussion presented in this paper provide a clear view of why classical electromagnetic theory is relativistic in its essence.

physics.class-ph↗

arXiv2022

Few-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification. In the task of few-shot learning, overfitting is a tough problem mainly due to the mismatch between training and testing conditions. In this paper, we propose a few-shot speaker identification method which can alleviate the overfitting problem. In the proposed method, the model of a depthwise separable convolutional network with channel attention is trained with a prototypical loss function. Experimental datasets are extracted from three public speech corpora: Aishell-2, VoxCeleb1 and TORGO. Experimental results show that the proposed method exceeds state-of-the-art methods for few-shot speaker identification in terms of accuracy and F-score.

eess.AS↗

arXiv2022

Benchmarking Domain Generalization on EEG-based Emotion Recognition

Electroencephalography (EEG) based emotion recognition has demonstrated tremendous improvement in recent years. Specifically, numerous domain adaptation (DA) algorithms have been exploited in the past five years to enhance the generalization of emotion recognition models across subjects. The DA methods assume that calibration data (although unlabeled) exists in the target domain (new user). However, this assumption conflicts with the application scenario that the model should be deployed without the time-consuming calibration experiments. We argue that domain generalization (DG) is more reasonable than DA in these applications. DG learns how to generalize to unseen target domains by leveraging knowledge from multiple source domains, which provides a new possibility to train general models. In this paper, we for the first time benchmark state-of-the-art DG algorithms on EEG-based emotion recognition. Since convolutional neural network (CNN), deep brief network (DBN) and multilayer perceptron (MLP) have been proved to be effective emotion recognition models, we use these three models as solid baselines. Experimental results show that DG achieves an accuracy of up to 79.41\% on the SEED dataset for recognizing three emotions, indicting the potential of DG in zero-training emotion recognition when multiple sources are available.

eess.SP↗

arXiv2022

MixNN: A design for protecting deep learning models

In this paper, we propose a novel design, called MixNN, for protecting deep learning model structure and parameters. The layers in a deep learning model of MixNN are fully decentralized. It hides communication address, layer parameters and operations, and forward as well as backward message flows among non-adjacent layers using the ideas from mix networks. MixNN has following advantages: 1) an adversary cannot fully control all layers of a model including the structure and parameters, 2) even some layers may collude but they cannot tamper with other honest layers, 3) model privacy is preserved in the training phase. We provide detailed descriptions for deployment. In one classification experiment, we compared a neural network deployed in a virtual machine with the same one using the MixNN design on the AWS EC2. The result shows that our MixNN retains less than 0.001 difference in terms of classification accuracy, while the whole running time of MixNN is about 7.5 times slower than the one running on a single virtual machine.

cs.DC↗

arXiv2022

A Voxel Graph CNN for Object Classification with Event Cameras

Event cameras attract researchers' attention due to their low power consumption, high dynamic range, and extremely high temporal resolution. Learning models on event-based object classification have recently achieved massive success by accumulating sparse events into dense frames to apply traditional 2D learning methods. Yet, these approaches necessitate heavy-weight models and are with high computational complexity due to the redundant information introduced by the sparse-to-dense conversion, limiting the potential of event cameras on real-life applications. This study aims to address the core problem of balancing accuracy and model complexity for event-based classification models. To this end, we introduce a novel graph representation for event data to exploit their sparsity better and customize a lightweight voxel graph convolutional neural network (\textit{EV-VGCNN}) for event-based classification. Specifically, (1) using voxel-wise vertices rather than previous point-wise inputs to explicitly exploit regional 2D semantics of event streams while keeping the sparsity;(2) proposing a multi-scale feature relational layer (\textit{MFRL}) to extract spatial and motion cues from each vertex discriminatively concerning its distances to neighbors. Comprehensive experiments show that our model can advance state-of-the-art classification accuracy with extremely low model complexity (merely 0.84M parameters).

cs.CV↗

arXiv2022

Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation

As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones to extract features for RGB and depth images. They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion. We find that the essential reason for using two independent backbones is the "projection breakdown" problem. In the depth image plane, the projected 3D structure of the physical world is preserved by the 1D depth value and its built-in 2D pixel coordinate (UV). Any spatial transformation that modifies UV, such as resize, flip, crop, or pooling operations in the CNN pipeline, breaks the binding between the pixel value and UV coordinate. As a consequence, the 3D structure is no longer preserved by a modified depth image or feature. To address this issue, we propose a simple yet effective method denoted as Uni6D that explicitly takes the extra UV data along with RGB-D images as input. Our method has a Unified CNN framework for 6D pose estimation with a single CNN backbone. In particular, the architecture of our method is based on Mask R-CNN with two extra heads, one named RT head for directly predicting 6D pose and the other named abc head for guiding the network to map the visible points to their coordinates in the 3D model as an auxiliary module. This end-to-end approach balances simplicity and accuracy, achieving comparable accuracy with state of the arts and 7.2x faster inference speed on the YCB-Video dataset.

cs.CV↗

arXiv2022

Cluster-based ensemble learning for wind power modeling with meteorological wind data

Optimal implementation and monitoring of wind energy generation hinge on reliable power modeling that is vital for understanding turbine control, farm operational optimization, and grid load balance. Based on the idea of similar wind condition leads to similar wind power; this paper constructs a modeling scheme that orderly integrates three types of ensemble learning algorithms, bagging, boosting, and stacking, and clustering approaches to achieve optimal power modeling. It also investigates applications of different clustering algorithms and methodology for determining cluster numbers in wind power modeling. The results reveal that all ensemble models with clustering exploit the intrinsic information of wind data and thus outperform models without it by approximately 15% on average. The model with the best farthest first clustering is computationally rapid and performs exceptionally well with an improvement of around 30%. The modeling is further boosted by about 5% by introducing stacking that fuses ensembles with varying clusters. The proposed modeling framework thus demonstrates promise by delivering efficient and robust modeling performance.

cs.LG↗

arXiv2022

Knowledge distillation with error-correcting transfer learning for wind power prediction

Wind power prediction, especially for turbines, is vital for the operation, controllability, and economy of electricity companies. Hybrid methodologies combining advanced data science with weather forecasting have been incrementally applied to the predictions. Nevertheless, individually modeling massive turbines from scratch and downscaling weather forecasts to turbine size are neither easy nor economical. Aiming at it, this paper proposes a novel framework with mathematical underpinnings for turbine power prediction. This framework is the first time to incorporate knowledge distillation into energy forecasting, enabling accurate and economical constructions of turbine models by learning knowledge from the well-established park model. Besides, park-scale weather forecasts non-explicitly are mapped to turbines by transfer learning of predicted power errors, achieving model correction for better performance. The proposed framework is deployed on five turbines featuring various terrains in an Arctic wind park, the results are evaluated against the competitors of ablation investigation. The major findings reveal that the proposed framework, developed on favorable knowledge distillation and transfer learning parameters tuning, yields performance boosts from 3.3 % to 23.9 % over its competitors. This advantage also exists in terms of wind energy physics and computing efficiency, which are verified by the prediction quality rate and calculation time.

cs.LG↗

arXiv2022

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.

cs.CV↗