arXiv subjects

Qi Wang

Publications and source records attributed to Qi Wang.

At least 343 records · Page 19Linked to original sources

arXiv2024

Inclusive Emotion Technologies: Addressing the Needs of d/Deaf and Hard of Hearing Learners in Video-Based Learning

Accessibility efforts for d/Deaf and hard of hearing (DHH) learners in video-based learning have mainly focused on captions and interpreters, with limited attention to learners' emotional awareness--an important yet challenging skill for effective learning. Current emotion technologies are designed to support learners' emotional awareness and social needs; however, little is known about whether and how DHH learners could benefit from these technologies. Our study explores how DHH learners perceive and use emotion data from two collection approaches, self-reported and automatic emotion recognition (AER), in video-based learning. By comparing the use of these technologies between DHH (N=20) and hearing learners (N=20), we identified key differences in their usage and perceptions: 1) DHH learners enhanced their emotional awareness by rewatching the video to self-report their emotions and called for alternative methods for self-reporting emotion, such as using sign language or expressive emoji designs; and 2) while the AER technology could be useful for detecting emotional patterns in learning experiences, DHH learners expressed more concerns about the accuracy and intrusiveness of the AER data. Our findings provide novel design implications for improving the inclusiveness of emotion technologies to support DHH learners, such as leveraging DHH peer learners' emotions to elicit reflections.

cs.HC↗

arXiv2024

Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera

The irregular contour representation is one of the tough challenges in scene text detection. Although segmentation-based methods have achieved significant progress with the help of flexible pixel prediction, the overlap of geographically close texts hinders detecting them separately. To alleviate this problem, some shrink-based methods predict text kernels and expand them to restructure texts. However, the text kernel is an artificial object with incomplete semantic features that are prone to incorrect or missing detection. In addition, different from the general objects, the geometry features (aspect ratio, scale, and shape) of scene texts vary significantly, which makes it difficult to detect them accurately. To consider the above problems, we propose an effective spotlight text detector (STD), which consists of a spotlight calibration module (SCM) and a multivariate information extraction module (MIEM). The former concentrates efforts on the candidate kernel, like a camera focus on the target. It obtains candidate features through a mapping filter and calibrates them precisely to eliminate some false positive samples. The latter designs different shape schemes to explore multiple geometric features for scene texts. It helps extract various spatial relationships to improve the model's ability to recognize kernel regions. Ablation studies prove the effectiveness of the designed SCM and MIEM. Extensive experiments verify that our STD is superior to existing state-of-the-art methods on various datasets, including ICDAR2015, CTW1500, MSRA-TD500, and Total-Text.

cs.CV↗

arXiv2024

Focus Entirety and Perceive Environment for Arbitrary-Shaped Text Detection

Due to the diversity of scene text in aspects such as font, color, shape, and size, accurately and efficiently detecting text is still a formidable challenge. Among the various detection approaches, segmentation-based approaches have emerged as prominent contenders owing to their flexible pixel-level predictions. However, these methods typically model text instances in a bottom-up manner, which is highly susceptible to noise. In addition, the prediction of pixels is isolated without introducing pixel-feature interaction, which also influences the detection performance. To alleviate these problems, we propose a multi-information level arbitrary-shaped text detector consisting of a focus entirety module (FEM) and a perceive environment module (PEM). The former extracts instance-level features and adopts a top-down scheme to model texts to reduce the influence of noises. Specifically, it assigns consistent entirety information to pixels within the same instance to improve their cohesion. In addition, it emphasizes the scale information, enabling the model to distinguish varying scale texts effectively. The latter extracts region-level information and encourages the model to focus on the distribution of positive samples in the vicinity of a pixel, which perceives environment information. It treats the kernel pixels as positive samples and helps the model differentiate text and kernel features. Extensive experiments demonstrate the FEM's ability to efficiently support the model in handling different scale texts and confirm the PEM can assist in perceiving pixels more accurately by focusing on pixel vicinities. Comparisons show the proposed model outperforms existing state-of-the-art approaches on four public datasets.

cs.CV↗

arXiv2024

The well-posedness and regularity of the Non-stationary Stokes and Navier-Stokes equations with the friction-type interface condition

The friction-type interface condition (FIC) is introduced to describe the phenomenon of the slip and leak of fluid flow on the interface happens only when the difference of stress force is above a threshold. The FIC involves the subdifferential and can be regarded as an intermediate form of the Dirichlet and the Neumann boundary conditions. This work is devoted to the well-posedness of the non-stationary (Navier-)Stokes equations with FIC in 2D and 3D, the weak forms of which are parabolic variational inequalities of the second type. We establish the existence theorems using the regularization technique and the Galerkin method. For the Stokes case, we prove the global unique existence and investigate the $H^2$ regularity. In the case of 2D Navier-Stokes equation, we show the global unique existence of the weak and strong solutions, respectively. For the Navier-Stokes case in 3D, we demonstrate the global existence of the weak solution and the local unique existence of the strong solution.

math.AP↗

arXiv2024

Implicit Government Guarantee Measurement Based on PMC Index Model

The implicit government guarantee hampers the recognition and management of risks by all stakeholders in the bond market, and it has led to excessive debt for local governments or state-owned enterprises. To prevent the risk of local government debt defaults and reduce investors' expectations of implicit government guarantees, various regulatory departments have issued a series of policy documents related to municipal investment bonds. By employing text mining techniques on policy documents related to municipal investment bond, and utilizing the PMC index model to assess the effectiveness of policy documents. This paper proposes a novel method for quantifying the intensity of implicit governmental guarantees based on PMC index model. The intensity of implicit governmental guarantees is inversely correlated with the PMC index of policies aimed at de-implicitizing governmental guarantees. Then as these policies become more effective, the intensity of implicit governmental guarantees diminishes correspondingly. These findings indicate that recent policies related to municipal investment bond have indeed succeeded in reducing implicit governmental guarantee intensity, and these policies have achieved the goal of risk management. Furthermore, it was showed that the intensity of implicit governmental guarantee affected by diverse aspects of these policies such as effectiveness, clarity, and specificity, as well as incentive and assurance mechanisms.

q-fin.GN↗

arXiv2024

Scalable Reshaping of Diamond Particles via Programmable Nanosculpting

Diamond particles have many interesting properties and possible applications. However, producing diamond particles with well-defined shapes at scale is challenging because diamonds are chemically inert and extremely hard. Here, we show air oxidation, a routine method for purifying diamonds, can be used to precisely shape diamond particles at scale. By exploiting the distinct reactivities of different crystal facets and defects inside the diamond, layer-by-layer outward-to-inward and inward-to-outward oxidation produced diverse diamond shapes including sphere, twisted surface, pyramidal islands, inverted pyramids, nano-flowers, and hollow polygons. The nanosculpted diamonds had more and finer features that enabled them to outperform the original raw diamonds in various applications. Using experimental observations and Monte Carlo simulations, we built a shape library that guides the design and fabrication of diamond particles with well-defined shapes and functional value. Our study presents a simple, economical and scalable way to produce shape-customized diamonds for various photonics, catalysis, quantum and information technology applications.

cond-mat.mtrl-sci↗

arXiv2024

Spatial Deep Convolutional Neural Networks

Spatial prediction problems often use Gaussian process models, which can be computationally burdensome in high dimensions. Specification of an appropriate covariance function for the model can be challenging when complex non-stationarities exist. Recent work has shown that pre-computed spatial basis functions and a feed-forward neural network can capture complex spatial dependence structures while remaining computationally efficient. This paper builds on this literature by tailoring spatial basis functions for use in convolutional neural networks. Through both simulated and real data, we demonstrate that this approach yields more accurate spatial predictions than existing methods. Uncertainty quantification is also considered.

stat.ME↗

arXiv2024

Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods

With the rise of deep learning technology in practical applications, Convolutional Neural Networks (CNNs) have been able to assist humans in solving many real-world problems. To enhance the performance of CNNs, numerous network architectures have been explored. Some of these architectures are designed based on the accumulated experience of researchers over time, while others are designed through neural architecture search methods. The improvements made to CNNs by the aforementioned methods are quite significant, but most of the improvement methods are limited in reality by model size and environmental constraints, making it difficult to fully realize the improved performance. In recent years, research has found that many CNN structures can be explained by the discretization of ordinary differential equations. This implies that we can design theoretically supported deep network structures using higher-order numerical difference methods. It should be noted that most of the previous CNN model structures are based on low-order numerical methods. Therefore, considering that the accuracy of linear multi-step numerical difference methods is higher than that of the forward Euler method, this paper proposes a stacking scheme based on the linear multi-step method. This scheme enhances the performance of ResNet without increasing the model size and compares it with the Runge-Kutta scheme. The experimental results show that the performance of the stacking scheme proposed in this paper is superior to existing stacking schemes (ResNet and HO-ResNet), and it has the capability to be extended to other types of neural networks.

cs.LG↗

arXiv2024

Topological Quantum Materials with Kagome Lattice

In this account, we will give an overview of our research progress on novel quantum properties in topological quantum materials with kagome lattice. Here, there are mainly two categories of kagome materials: magnetic kagome materials and nonmagnetic ones. On one hand, magnetic kagome materials mainly focus on the 3d transition-metal-based kagome systems, including Fe$_3$Sn$_2$, Co$_3$Sn$_2$S$_2$, YMn6Sn6, FeSn, and CoSn. The interplay between magnetism and topological bands manifests vital influence on the electronic response. For example, the existence of massive Dirac or Weyl fermions near the Fermi level signicantly enhances the magnitude of Berry curvature in momentum space, leading to a large intrinsic anomalous Hall effect. In addition, the peculiar frustrated structure of kagome materials enables them to host a topologically protected skyrmion lattice or noncoplaner spin texture, yielding a topological Hall effect that arises from the realspace Berry phase. On the other hand, nonmagnetic kagome materials in the absence of longrange magnetic order include CsV3Sb5 with the coexistence of superconductivity, charge density wave state, and band topology and van der Waals semiconductor Pd$_3$P$_2$S$_8$. For these two kagome materials, the tunability of electric response in terms of high pressure or carrier doping helps to reveal the interplay between electronic correlation effects and band topology and discover the novel emergent quantum phenomena in kagome materials.

cond-mat.supr-con↗

arXiv2024

EaDeblur-GS: Event assisted 3D Deblur Reconstruction with Gaussian Splatting

3D deblurring reconstruction techniques have recently seen significant advancements with the development of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). Although these techniques can recover relatively clear 3D reconstructions from blurry image inputs, they still face limitations in handling severe blurring and complex camera motion. To address these issues, we propose Event-assisted 3D Deblur Reconstruction with Gaussian Splatting (EaDeblur-GS), which integrates event camera data to enhance the robustness of 3DGS against motion blur. By employing an Adaptive Deviation Estimator (ADE) network to estimate Gaussian center deviations and using novel loss functions, EaDeblur-GS achieves sharp 3D reconstructions in real-time, demonstrating performance comparable to state-of-the-art methods.

cs.CV↗

arXiv2024

Single-Loop Deterministic and Stochastic Interior-Point Algorithms for Nonlinearly Constrained Optimization

An interior-point algorithm framework is proposed, analyzed, and tested for solving nonlinearly constrained continuous optimization problems. The main setting of interest is when the objective and constraint functions may be nonlinear and/or nonconvex, and when constraint values and derivatives are tractable to compute, but objective function values and derivatives can only be estimated. The algorithm is intended primarily for a setting that is similar for stochastic-gradient methods for unconstrained optimization, namely, the setting when stochastic-gradient estimates are available and employed in place of gradients of the objective, and when no objective function values (nor estimates of them) are employed. This is achieved by the interior-point framework having a single-loop structure rather than the nested-loop structure that is typical of contemporary interior-point methods. For completeness, convergence guarantees for the framework are provided both for deterministic and stochastic settings. Numerical experiments show that the algorithm yields good performance on a large set of test problems.

math.OC↗

arXiv2024

On $τ$-tilting finiteness of symmetric algebras of polynomial growth

In this paper, we report on the $τ$-tilting finiteness of some classes of finite-dimensional algebras over an algebraically closed field, including symmetric algebras of polynomial growth, $0$-Hecke algebras and $0$-Schur algebras. Consequently, we find that derived equivalence preserves the $τ$-tilting finiteness over symmetric algebras of polynomial growth, and self-injective cellular algebras of polynomial growth are $τ$-tilting finite. Furthermore, the representation-finiteness and $τ$-tilting finiteness over $0$-Hecke algebras and $0$-Schur algebras (with few exceptions) coincide.

math.RT↗

arXiv2024

Reduce Computational Complexity for Convolutional Layers by Skipping Zeros

Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration. Within convolutional layers, there are three types of operators: convolution used in forward propagation, deconvolution and dilated-convolution utilized in backward propagation. During the execution of these operators, zeros are typically added to tensors, leading to redundant calculations and unnecessary strain on hardware. To circumvent these inefficiencies, we propose the C-K-S algorithm, accompanied by efficient GPU implementations. C-K-S trims filters to exclude zero-padding. For deconvolution and dilated-convolution, C-K-S transforms sparse tensors into dense tensors, and standardizes the local computational rules to simplify the hardware control. The experimental results demonstrate that C-K-S offers good performance in terms of speed and convergence, surpassing the capabilities of PyTorch and cuDNN in certain scenarios.

cs.LG↗

arXiv2024

A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot

Traditional license plate detection and recognition models are often trained on closed datasets, limiting their ability to handle the diverse license plate formats across different regions. The emergence of large-scale pre-trained models has shown exceptional generalization capabilities, enabling few-shot and zero-shot learning. We propose OneShotLP, a training-free framework for video-based license plate detection and recognition, leveraging these advanced models. Starting with the license plate position in the first video frame, our method tracks this position across subsequent frames using a point tracking module, creating a trajectory of prompts. These prompts are input into a segmentation module that uses a promptable large segmentation model to generate local masks of the license plate regions. The segmented areas are then processed by multimodal large language models (MLLMs) for accurate license plate recognition. OneShotLP offers significant advantages, including the ability to function effectively without extensive training data and adaptability to various license plate styles. Experimental results on UFPR-ALPR and SSIG-SegPlate datasets demonstrate the superior accuracy of our approach compared to traditional methods. This highlights the potential of leveraging pre-trained models for diverse real-world applications in intelligent transportation systems. The code is available at https://github.com/Dinghaoxuan/OneShotLP.

cs.CV↗

arXiv2024

EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

In this work, we tackle the challenge of enhancing the realism and expressiveness in talking head video generation by focusing on the dynamic and nuanced relationship between audio cues and facial movements. We identify the limitations of traditional techniques that often fail to capture the full spectrum of human expressions and the uniqueness of individual facial styles. To address these issues, we propose EMO, a novel framework that utilizes a direct audio-to-video synthesis approach, bypassing the need for intermediate 3D models or facial landmarks. Our method ensures seamless frame transitions and consistent identity preservation throughout the video, resulting in highly expressive and lifelike animations. Experimental results demonsrate that EMO is able to produce not only convincing speaking videos but also singing videos in various styles, significantly outperforming existing state-of-the-art methodologies in terms of expressiveness and realism.

cs.CV↗

arXiv2024

Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description

Zero sample learning is an effective method for data deficiency. The existing embedded zero sample learning methods only use the known classes to construct the embedded space, so there is an overfitting of the known classes in the testing process. This project uses category semantic similarity measures to classify multiple tags. This enables it to incorporate unknown classes that have the same meaning as currently known classes into the vector space when it is built. At the same time, most of the existing zero sample learning algorithms directly use the depth features of medical images as input, and the feature extraction process does not consider semantic information. This project intends to take ELMo-MCT as the main task and obtain multiple visual features related to the original image through self-attention mechanism. In this paper, a large number of experiments are carried out on three zero-shot learning reference datasets, and the best harmonic average accuracy is obtained compared with the most advanced algorithms.

cs.CV↗

arXiv2024

OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person

Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent results. While diffusion models, such as Stable Diffusion series, have shown their capability in creating high-quality and photorealistic images, they encounter formidable challenges in conditional generation scenarios like VTON. Specifically, these models struggle to maintain a balance between control and consistency when generating images for virtual clothing trials. OutfitAnyone addresses these limitations by leveraging a two-stream conditional diffusion model, enabling it to adeptly handle garment deformation for more lifelike results. It distinguishes itself with scalability-modulating factors such as pose, body shape and broad applicability, extending from anime to in-the-wild images. OutfitAnyone's performance in diverse scenarios underscores its utility and readiness for real-world deployment. For more details and animated results, please see \url{https://humanaigc.github.io/outfit-anyone/}.

cs.CV↗

arXiv2024

Annealing-induced long-range charge density wave order in magnetic kagome FeGe: fluctuations and disordered structure

Charge density wave (CDW) in kagome materials with the geometric frustration is able to carry unconventional characteristics. Recently, a CDW has been observed below the antiferromagnetic order in kagome FeGe, in which magnetism and CDW are intertwined to form an emergent quantum ground state. However, the CDW is only short-ranged and the structural modulation originating from it has yet to be determined experimentally. Here we realize a long-range CDW order by post-annealing process, and resolve the structure model through single crystal x-ray diffraction. Occupational disorder of Ge resulting from short-range CDW correlations above $T_\mathrm{CDW}$ is identified from structure refinements. The partial dimerization of Ge along the $c$ axis is unveiled to be the dominant distortion for the CDW. Occupational disorder of Ge is also proved to exist in the CDW phase due to the random selection of partially dimerized Ge sites. Our work provides useful insights for understanding the unconventional nature of the CDW in FeGe.

cond-mat.str-el↗