Searcharxiv⌕ Search

arXiv subjects

Xin Zhou

Publications and source records attributed to Xin Zhou.

At least 271 records · Page 15Linked to original sources
arXiv2023

EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Images

Structure-from-Motion is a technology used to obtain scene structure through image collection, which is a fundamental problem in computer vision. For unordered Internet images, SfM is very slow due to the lack of prior knowledge about image overlap. For sequential images, knowing the large overlap between adjacent frames, SfM can adopt a variety of acceleration strategies, which are only applicable to sequential data. To further improve the reconstruction efficiency and break the gap of strategies between these two kinds of data, this paper presents an efficient covisibility-based incremental SfM. Different from previous methods, we exploit covisibility and registration dependency to describe the image connection which is suitable to any kind of data. Based on this general image connection, we propose a unified framework to efficiently reconstruct sequential images, unordered images, and the mixture of these two. Experiments on the unordered images and mixed data verify the effectiveness of the proposed method, which is three times faster than the state of the art on feature matching, and an order of magnitude faster on reconstruction without sacrificing the accuracy. The source code is publicly available at https://github.com/openxrlab/xrsfm

cs.CV↗
arXiv2023

Observation of zero resistance above 100$^\circ$ K in Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O

Room-temperature superconductivity has always been regarded as the ultimate goal in the fields of solid-state physics and materials science, with its realization holding revolutionary significance, capable of triggering significant changes in energy transmission and storage. However, achieving it poses various challenges. Recent research revealed that material Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O displays room-temperature superconductivity under atmospheric pressure, sparking global interest in further exploration. Here, we utilized solid-phase synthesis to obtain a polycrystalline sample of Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O. X-ray diffraction confirmed its structural consistency with referenced literature. Zero resistance, which is important evidence for superconductivity, was observed above 100$^\circ$ K under ambient pressure in our experiment. Our finding indicates that Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O is a possible candidate for searching high-temperature superconductors.

cond-mat.supr-con↗
arXiv2023

The Role of Magnetic Fields in the Formation of the Filamentary Infrared Dark Cloud G11.11-0.12

We report on the near-infrared polarimetric observations of G11.11-0.12 (hereafter G11) obtained with SIRPOL on the 1.4 m IRSF telescope. The starlight polarisation of the background stars reveals the on-sky component of magnetic fields in G11, and these are consistent with the field orientation observed from polarised dust emission at $850\,μ$m. The magnetic fields in G11 are perpendicular to the filament, and are independent of the filament's orientation relative to the Galactic plane. The field strength in the envelope of G11 is in the range $50-100\,μ$G, derived from two methods. The analyses of the magnetic fields and gas velocity dispersion indicate that the envelope of G11 is supersonic but sub-Alfv{é}nic. The critical mass-to-flux ratio in the envelope of G11 is close to 1 and increases to $\gtrsim 1$ on the spine of G11. The relative weights on the importance of magnetic fields, turbulence and gravity indicate that gravity dominates the dynamical state of G11, but with significant contribution from magnetic fields. The field strength, $|\mathbf{B}|$, increases slower than the gas density, $n$, from the envelope to the spine of G11, characterized by $|\mathbf{B}|\propto n^{0.3}$. The observed strength and orientation of magnetic fields in G11 imply that supersonic and sub-Alfv{é}nic gas flow is channelled by the strong magnetic fields and is assembled into filaments perpendicular to the magnetic fields. The formation of low-mass stars is enhanced in the filaments with high column density, in agreement with the excess of low-mass protostars detected in the densest regions of G11.

astro-ph.GA↗
arXiv2023

Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER

As the categories of named entities rapidly increase, the deployed NER models are required to keep updating toward recognizing more entity types, creating a demand for class-incremental learning for NER. Considering the privacy concerns and storage constraints, the standard paradigm for class-incremental NER updates the models with training data only annotated with the new classes, yet the entities from other entity classes are unlabeled, regarded as "Non-entity" (or "O"). In this work, we conduct an empirical study on the "Unlabeled Entity Problem" and find that it leads to severe confusion between "O" and entities, decreasing class discrimination of old classes and declining the model's ability to learn new classes. To solve the Unlabeled Entity Problem, we propose a novel representation learning method to learn discriminative representations for the entity classes and "O". Specifically, we propose an entity-aware contrastive learning method that adaptively detects entity clusters in "O". Furthermore, we propose two effective distance-based relabeling strategies for better learning the old classes. We introduce a more realistic and challenging benchmark for class-incremental NER, and the proposed method achieves up to 10.62\% improvement over the baseline methods.

cs.CL↗
arXiv2023

Molecular environment of the thermal composite supernova remnant G352.7$-$0.1

Galactic supernova remnants (SNRs) play an important role in our understanding of supernovae and their feedback on the interstellar environment. SNR G352.7$-$0.1 is special for its thermal composite morphology and double-ring structure. We have performed spectroscopic mapping in $^{12}$CO and $^{13}$CO $J=2$-1 lines toward G352.7$-$0.1 with the Atacama Pathfinder Experiment telescope. Broad $^{12}$CO lines are found in the northeastern ring at a local-standard-of-rest velocity range of $\sim-50$-$-30$ km s$^{-1}$, suggesting that the remnant is interacting with molecular clouds (MCs) at $\sim-51$ km s$^{-1}$. Thus, we adopt a distance of $\sim10.5$ kpc for this SNR. The momentum and kinetic energy of the shocked gas along the line of sight are estimated to be $\sim10^2{\rm M_{sun}}$ km s$^{-1}$ and $\sim10^{46}$ erg, respectively. We also find an expanding structure around the remnant, which is possibly related to the wind-blown bubble of the progenitor star. From the Fermi-LAT data in an energy range of 0.1-500 GeV, we find no gamma-ray counterparts of G352.7$-$0.1.

astro-ph.HE↗
arXiv2023

Digital Twinning of the Human Ventricular Activation Sequence to Clinical 12-lead ECGs and Magnetic Resonance Imaging Using Realistic Purkinje Networks for in Silico Clinical Trials

Cardiac in silico clinical trials can virtually assess the safety and efficacy of therapies using human-based modelling and simulation. These technologies can provide mechanistic explanations for clinically observed pathological behaviour. Designing virtual cohorts for in silico trials requires exploiting clinical data to capture the physiological variability in the human population. The clinical characterisation of ventricular activation and the Purkinje network is challenging, especially non-invasively. Our study aims to present a novel digital twinning pipeline that can efficiently generate and integrate Purkinje networks into human multiscale biventricular models based on subject-specific clinical 12-lead electrocardiogram and magnetic resonance recordings. Essential novel features of the pipeline are the human-based Purkinje network generation method, personalisation considering ECG R wave progression as well as QRS morphology, and translation from reduced-order Eikonal models to equivalent biophysically-detailed monodomain ones. We demonstrate ECG simulations in line with clinical data with clinical image-based multiscale models with Purkinje in four control subjects and two hypertrophic cardiomyopathy patients (simulated and clinical QRS complexes with Pearson's correlation coefficients > 0.7). Our methods also considered possible differences in the density of Purkinje myocardial junctions in the Eikonal-based inference as regional conduction velocities. These differences translated into regional coupling effects between Purkinje and myocardial models in the monodomain formulation. In summary, we demonstrate a digital twin pipeline enabling simulations yielding clinically-consistent ECGs with clinical CMR image-based biventricular multiscale models, including personalised Purkinje in healthy and cardiac disease conditions.

physics.med-ph↗
arXiv2023

Molecular Clouds in the Galactic Plane from $l$ = [59.75$^\circ$, 74.75$^\circ$] and $b$ = [$-$5.25$^\circ$, +5.25$^\circ$]

In this paper we present the distribution of molecular gas in the Milky Way Galactic plane from $l$ = [59.75, 74.75]$^{\circ}$ and $b$ = [${-}$5.25, +5.25]$^{\circ}$, using the MWISP $^{12}$CO/$^{13}$CO/$\rm {C}^{18}{O}$ emission line data. The molecular gas in this region can be mainly attributed to the Local spur, Local arm, Perseus arm, and Outer arm. Statistics of the physical properties of the molecular gas in each arm, such as excitation temperature, optical depth, and column density, are presented. Using the DBSCAN algorithm, we identified 15 extremely distant molecular clouds with kinematic distances of 14.72$-$17.77 kpc and masses of 363$-$520 M$_{\odot}$, which we find could be part of the Outer Scutum-Centaurus (OSC) arm identified by \cite{2011ApJ...734L..24D} and \cite{2015ApJ...798L..27S}. It is also possible that, 12 of these 15 extremely distant molecular clouds constitute an independent structure between the Outer and the OSC arms or a spur. There exist two Gaussian components in the vertical distribution of the molecular gas in the Perseus spiral arm. These two Gaussian components correspond to two giant filaments parallel to the Galactic plane. We find an upward warping of the molecular gas in the Outer spiral arm with a displacement of around 270 pc with respect to the Galactic mid-plane.

astro-ph.GA↗
arXiv2023

InstaGrasp: An Entirely 3D Printed Adaptive Gripper with TPU Soft Elements and Minimal Assembly Time

Fabricating existing and popular open-source adaptive robotic grippers commonly involves using multiple professional machines, purchasing a wide range of parts, and tedious, time-consuming assembly processes. This poses a significant barrier to entry for some robotics researchers and drives others to opt for expensive commercial alternatives. To provide both parties with an easier and cheaper (under 100GBP) solution, we propose a novel adaptive gripper design where every component (with the exception of actuators and the screws that come packaged with them) can be fabricated on a hobby-grade 3D printer, via a combination of inexpensive and readily available PLA and TPU filaments. This approach means that the gripper's tendons, flexure joints and finger pads are now printed, as a replacement for traditional string-tendons and molded urethane flexures and pads. A push-fit systems results in an assembly time of under 10 minutes. The gripper design is also highly modular and requires only a few minutes to replace any part, leading to extremely user-friendly maintenance and part modifications. An extensive stress test has shown a level of durability more than suitable for research, whilst grasping experiments (with perturbations) using items from the YCB object set has also proven its mechanical adaptability to be highly satisfactory.

cs.RO↗
arXiv2023

Sequential Best-Arm Identification with Application to Brain-Computer Interface

A brain-computer interface (BCI) is a technology that enables direct communication between the brain and an external device or computer system. It allows individuals to interact with the device using only their thoughts, and holds immense potential for a wide range of applications in medicine, rehabilitation, and human augmentation. An electroencephalogram (EEG) and event-related potential (ERP)-based speller system is a type of BCI that allows users to spell words without using a physical keyboard, but instead by recording and interpreting brain signals under different stimulus presentation paradigms. Conventional non-adaptive paradigms treat each word selection independently, leading to a lengthy learning process. To improve the sampling efficiency, we cast the problem as a sequence of best-arm identification tasks in multi-armed bandits. Leveraging pre-trained large language models (LLMs), we utilize the prior knowledge learned from previous tasks to inform and facilitate subsequent tasks. To do so in a coherent way, we propose a sequential top-two Thompson sampling (STTS) algorithm under the fixed-confidence setting and the fixed-budget setting. We study the theoretical property of the proposed algorithm, and demonstrate its substantial empirical improvement through both synthetic data analysis as well as a P300 BCI speller simulator example.

cs.HC↗
arXiv2023

Bootstrap Latent Representations for Multi-modal Recommendation

This paper studies the multi-modal recommendation problem, where the item multi-modality information (e.g., images and textual descriptions) is exploited to improve the recommendation accuracy. Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e.g., user-user or item-item relation graph) to augment the learned representations of users and/or items. These representations are often propagated and aggregated on auxiliary graphs using graph convolutional networks, which can be prohibitively expensive in computation and memory, especially for large graphs. Moreover, existing multi-modal recommendation methods usually leverage randomly sampled negative examples in Bayesian Personalized Ranking (BPR) loss to guide the learning of user/item representations, which increases the computational cost on large graphs and may also bring noisy supervision signals into the training process. To tackle the above issues, we propose a novel self-supervised multi-modal recommendation model, dubbed BM3, which requires neither augmentations from auxiliary graphs nor negative samples. Specifically, BM3 first bootstraps latent contrastive views from the representations of users and items with a simple dropout augmentation. It then jointly optimizes three multi-modal objectives to learn the representations of users and items by reconstructing the user-item interaction graph and aligning modality features under both inter- and intra-modality perspectives. BM3 alleviates both the need for contrasting with negative examples and the complex graph augmentation from an additional target network for contrastive view generation. We show BM3 outperforms prior recommendation models on three datasets with number of nodes ranging from 20K to 200K, while achieving a 2-9X reduction in training time. Our code is available at https://github.com/enoche/BM3.

cs.IR↗
arXiv2023

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. In this paper, we propose a self-supervised collaborative filtering framework (SelfCF), that is specially designed for recommender scenario with implicit feedback. The proposed SelfCF framework simplifies the Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SelfCF is to augment the output embeddings generated by backbone networks, because it is infeasible to augment raw input of user/item ids. We propose and study three output perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. We conduct comprehensive experiments on four datasets to show that our framework may achieve even better recommendation accuracy than the encapsulated supervised counterpart with a 2$\times$--4$\times$ faster training speed. We also show that SelfCF can boost up the accuracy by up to 17.79% on average, compared with a self-supervised framework BUIR.

cs.IR↗
arXiv2023

Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis

Denoising diffusion probabilistic models (DDPMs) are a class of powerful generative models. The past few years have witnessed the great success of DDPMs in generating high-fidelity samples. A significant limitation of the DDPMs is the slow sampling procedure. DDPMs generally need hundreds or thousands of sequential function evaluations (steps) of neural networks to generate a sample. This paper aims to develop a fast sampling method for DDPMs requiring much fewer steps while retaining high sample quality. The inference process of DDPMs approximates solving the corresponding diffusion ordinary differential equations (diffusion ODEs) in the continuous limit. This work analyzes how the backward error affects the diffusion ODEs and the sample quality in DDPMs. We propose fast sampling through the \textbf{Restricting Backward Error schedule (RBE schedule)} based on dynamically moderating the long-time backward error. Our method accelerates DDPMs without any further training. Our experiments show that sampling with an RBE schedule generates high-quality samples within only 8 to 20 function evaluations on various benchmark datasets. We achieved 12.01 FID in 8 function evaluations on the ImageNet $128\times128$, and a $20\times$ speedup compared with previous baseline samplers.

cs.CV↗
arXiv2023

Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model

We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use classical generative architecture, we apply the Denoising Diffusion Probabilistic Model to this task, synthesizing diverse motion results under the guidance of texts. The diffusion model converts white noise into structured 3D motion by a Markov process with a series of denoising steps and is efficiently trained by optimizing a variational lower bound. To achieve the goal of text-conditioned image synthesis, we use the classifier-free guidance strategy to fuse text embedding into the model during training. Our experiments demonstrate that our model achieves competitive results on HumanML3D test set quantitatively and can generate more visually natural and diverse examples. We also show with experiments that our model is capable of zero-shot generation of motions for unseen text guidance.

cs.CV↗
arXiv2023

PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking

Planar object tracking is a critical computer vision problem and has drawn increasing interest owing to its key roles in robotics, augmented reality, etc. Despite rapid progress, its further development, especially in the deep learning era, is largely hindered due to the lack of large-scale challenging benchmarks. Addressing this, we introduce PlanarTrack, a large-scale challenging planar tracking benchmark. Specifically, PlanarTrack consists of 1,000 videos with more than 490K images. All these videos are collected in complex unconstrained scenarios from the wild, which makes PlanarTrack, compared with existing benchmarks, more challenging but realistic for real-world applications. To ensure the high-quality annotation, each frame in PlanarTrack is manually labeled using four corners with multiple-round careful inspection and refinement. To our best knowledge, PlanarTrack, to date, is the largest and most challenging dataset dedicated to planar object tracking. In order to analyze the proposed PlanarTrack, we evaluate 10 planar trackers and conduct comprehensive comparisons and in-depth analysis. Our results, not surprisingly, demonstrate that current top-performing planar trackers degenerate significantly on the challenging PlanarTrack and more efforts are needed to improve planar tracking in the future. In addition, we further derive a variant named PlanarTrack$_{\mathbf{BB}}$ for generic object tracking from PlanarTrack. Our evaluation of 10 excellent generic trackers on PlanarTrack$_{\mathrm{BB}}$ manifests that, surprisingly, PlanarTrack$_{\mathrm{BB}}$ is even more challenging than several popular generic tracking benchmarks and more attention should be paid to handle such planar objects, though they are rigid. All benchmarks and evaluations will be released at the project webpage.

cs.CV↗
arXiv2023

Generation-based Code Review Automation: How Far Are We?

Code review is an effective software quality assurance activity; however, it is labor-intensive and time-consuming. Thus, a number of generation-based automatic code review (ACR) approaches have been proposed recently, which leverage deep learning techniques to automate various activities in the code review process (e.g., code revision generation and review comment generation). We find the previous works carry three main limitations. First, the ACR approaches have been shown to be beneficial in each work, but those methods are not comprehensively compared with each other to show their superiority over their peer ACR approaches. Second, general-purpose pre-trained models such as CodeT5 are proven to be effective in a wide range of Software Engineering (SE) tasks. However, no prior work has investigated the effectiveness of these models in ACR tasks yet. Third, prior works heavily rely on the Exact Match (EM) metric which only focuses on the perfect predictions and ignores the positive progress made by incomplete answers. To fill such a research gap, we conduct a comprehensive study by comparing the effectiveness of recent ACR tools as well as the general-purpose pre-trained models. The results show that a general-purpose pre-trained model CodeT5 can outperform other models in most cases. Specifically, CodeT5 outperforms the prior state-of-the-art by 13.4\%--38.9\% in two code revision generation tasks. In addition, we introduce a new metric namely Edit Progress (EP) to quantify the partial progress made by ACR tools. The results show that the rankings of models for each task could be changed according to whether EM or EP is being utilized. Lastly, we derive several insightful lessons from the experimental results and reveal future research directions for generation-based code review automation.

cs.SE↗
arXiv2023

Raising The Limit Of Image Rescaling Using Auxiliary Encoding

Normalizing flow models using invertible neural networks (INN) have been widely investigated for successful generative image super-resolution (SR) by learning the transformation between the normal distribution of latent variable $z$ and the conditional distribution of high-resolution (HR) images gave a low-resolution (LR) input. Recently, image rescaling models like IRN utilize the bidirectional nature of INN to push the performance limit of image upscaling by optimizing the downscaling and upscaling steps jointly. While the random sampling of latent variable $z$ is useful in generating diverse photo-realistic images, it is not desirable for image rescaling when accurate restoration of the HR image is more important. Hence, in places of random sampling of $z$, we propose auxiliary encoding modules to further push the limit of image rescaling performance. Two options to store the encoded latent variables in downscaled LR images, both readily supported in existing image file format, are proposed. One is saved as the alpha-channel, the other is saved as meta-data in the image header, and the corresponding modules are denoted as suffixes -A and -M respectively. Optimal network architectural changes are investigated for both options to demonstrate their effectiveness in raising the rescaling performance limit on different baseline models including IRN and DLV-IRN.

cs.CV↗
arXiv2023

Cubic singularities in binary linear electromechanical oscillators

Singularities arise in diverse disciplines and play a key role in both exploring fundamental laws of physics and making highly-sensitive sensors. Higher-order (>3) singularities, with further improved performance, however, usually require exquisite tuning of multiple (>3) coupled degrees of freedom or nonlinear control, thus severely limiting their applications in practice. Here we propose theoretically and confirm using mechanics experiments that, cubic singularities can be realized in a coupled binary system without any nonlinearity, only by observing the phase tomography of the driven response. By steering the cubic phase-tomographic singularities in an electrostatically-tunable micromechanical system, enhanced cubic-root response to frequency perturbation and voltage-controlled nonreciprocity are demonstrated. Our work opens up a new phase-tomographic method for interacted-system research and sheds new light on building and engineering advanced singular devices with simple and well-controllable elements, with a wide range of applications including precision metrology, portable nonreciprocal devices, and on-chip mechanical computing.

physics.app-ph↗
arXiv2023

Do We Really Need Complicated Model Architectures For Temporal Networks?

Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-pooling to summarize node information, and (3) an MLP-based link classifier that performs link prediction based on the outputs of the encoders. Despite its simplicity, GraphMixer attains an outstanding performance on temporal link prediction benchmarks with faster convergence and better generalization performance. These results motivate us to rethink the importance of simpler model architecture.

cs.LG↗