arXiv subjects

Hao Wu

Publications and source records attributed to Hao Wu.

At least 397 records · Page 22Linked to original sources

arXiv2025

Water Quality Data Imputation via A Fast Latent Factorization of Tensors with PID-based Optimizer

Water quality data can supply a substantial decision support for water resources utilization and pollution prevention. However, there are numerous missing values in water quality data due to inescapable factors like sensor failure, thereby leading to biased result for hydrological analysis and failing to support environmental governance decision accurately. A Latent Factorization of Tensors (LFT) with Stochastic Gradient Descent (SGD) proves to be an efficient imputation method. However, a standard SGD-based LFT model commonly surfers from the slow convergence that impairs its efficiency. To tackle this issue, this paper proposes a Fast Latent Factorization of Tensors (FLFT) model. It constructs an adjusted instance error into SGD via leveraging a nonlinear PID controller to incorporates the past, current and future information of prediction error for improving convergence rate. Comparing with state-of-art models in real world datasets, the results of experiment indicate that the FLFT model achieves a better convergence rate and higher accuracy.

cs.LG↗

arXiv2025

SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic

Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the evaluation of state-of-the-art algorithms. To address these limitations, we introduce SGA-INTERACT, the first 3D skeleton-based benchmark for group activity understanding. It features complex activities inspired by basketball tactics, emphasizing rich spatial interactions and long-term dependencies. SGA-INTERACT introduces Temporal Group Activity Localization (TGAL) task, extending group activity understanding to untrimmed sequences, filling the gap left by GAR as a standalone task. In addition to the benchmark, we propose One2Many, a novel framework that employs a pretrained 3D skeleton backbone for unified individual feature extraction. This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks. We conduct extensive evaluations on SGA-INTERACT using two skeleton-based methods, three RGB-based methods, and a proposed baseline within the One2Many framework. The general low performance of baselines highlights the benchmark's challenges, motivating advancements in group activity understanding.

cs.CV↗

arXiv2025

Multi-category solar radio burst detection based on task-aligned one-stage object detection model

Accurate identification of solar radio bursts (SRBs) is essential for advancing research in solar physics and predicting space weather. However, the majority of current studies mainly concentrate on detecting whether SRBs are present or absent, often focusing on only one particular type of burst. Moreover, the neural network models used for SRB detection are typically complex, involving a large number of parameters, which results in slower processing speeds. This study establishes a dataset encompassing Type II, Type III, Type IIIs, Type IV, and Type V SRBs collected from e-CALLISTO, including 8,752 SRB spectrum images and achieving annotations for 10,822 SRBs. We propose a multi-category SRB detection model based on task-aligned one-stage object detection (TOOD). TOOD can solve the problem of inconsistent predictions in classification and localization tasks, and it improves the detection recall rate. This model aligns classification and localization tasks and optimizes the neck network by incorporating a channel attention mechanism. This model achieves higher recall and accuracy with fewer parameters. This model can accurately detect five types of SBRs. The experimental results show that the model achieved an accuracy of 79.9\% (AP50) and a recall rate of 95.1\% on the SBRs dataset. A higher recall rate than other models means fewer SRBs are missed in automatic detection. The model we propose has the potential to make a substantial impact on solar physics research and space weather studies. Additionally, the findings in this paper could provide valuable insights for processing other small-sample astronomical datasets.The source code and data is available at https://github.com/onewangqianqian/MobileNetVitv2-TOOD.git.

astro-ph.IM↗

arXiv2025

Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems

Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems is a fundamental yet challenging problem in many fields of science and engineering. Existing methods face significant obstacles: Gaussian-based filters struggle with non-Gaussian distributions, while sequential Monte Carlo methods are computationally intensive and prone to particle degeneracy in high dimensions. Although generative models in machine learning have made significant progress in modeling high-dimensional non-Gaussian distributions, their inefficiency in online updating limits their applicability to filtering problems. To address these challenges, we propose a flow-based Bayesian filter (FBF) that integrates normalizing flows to construct a novel latent linear state-space model with Gaussian filtering distributions. This framework facilitates efficient density estimation and sampling using invertible transformations provided by normalizing flows, and it enables the construction of filters in a data-driven manner, without requiring prior knowledge of system dynamics or observation models. Numerical experiments demonstrate the superior accuracy and efficiency of FBF.

math.NA↗

arXiv2025

Learning-Augmented Frequent Directions

An influential paper of Hsu et al. (ICLR'19) introduced the study of learning-augmented streaming algorithms in the context of frequency estimation. A fundamental problem in the streaming literature, the goal of frequency estimation is to approximate the number of occurrences of items appearing in a long stream of data using only a small amount of memory. Hsu et al. develop a natural framework to combine the worst-case guarantees of popular solutions such as CountMin and CountSketch with learned predictions of high frequency elements. They demonstrate that learning the underlying structure of data can be used to yield better streaming algorithms, both in theory and practice. We simplify and generalize past work on learning-augmented frequency estimation. Our first contribution is a learning-augmented variant of the Misra-Gries algorithm which improves upon the error of learned CountMin and learned CountSketch and achieves the state-of-the-art performance of randomized algorithms (Aamand et al., NeurIPS'23) with a simpler, deterministic algorithm. Our second contribution is to adapt learning-augmentation to a high-dimensional generalization of frequency estimation corresponding to finding important directions (top singular vectors) of a matrix given its rows one-by-one in a stream. We analyze a learning-augmented variant of the Frequent Directions algorithm, extending the theoretical and empirical understanding of learned predictions to matrix streaming.

cs.LG↗

arXiv2025

Energy-efficient field-free unconventional spin-orbit torque magnetization switching dynamics in van der Waals heterostructures

Van der Waals (vdW) heterostructure of two-dimensional (2D) quantum materials offers a promising platform for efficient control of magnetization dynamics for non-volatile spin-based devices. However, energy-efficient field-free spin-orbit torque (SOT) switching and spin dynamics experiments to understand the basic SOT phenomena in all-2D vdW heterostructures are so far lacking. Here, we demonstrate energy-efficient field-free spin-orbit torque (SOT) switching and tunable magnetization dynamics in a vdW heterostructure comprising out-of-plane magnet Fe3GaTe2 and topological Weyl semimetal TaIrTe4. We measured the non-linear second harmonic Hall signal in TaIrTe4 /Fe3GaTe2 devices to evaluate the SOT-induced magnetization dynamics, which is characterized by a large and tunable out-of-plane damping-like torque. Energy-efficient and deterministic field-free SOT magnetization switching is achieved at room temperature with a very low current density. First-principles calculations unveil the origin of the unconventional charge-spin conversion phenomena, considering the crystal symmetry and electronic structure of TaIrTe4. These results establish that all-vdW heterostructures provide a promising route to energy-efficient, field-free, and tunable SOT-based spintronic devices.

cond-mat.mes-hall↗

arXiv2025

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting

In practice, physical spatiotemporal forecasting can suffer from data scarcity, because collecting large-scale data is non-trivial, especially for extreme events. Hence, we propose \method{}, a novel probabilistic framework to realize iterative self-training with new self-ensemble strategies, achieving better physical consistency and generalization on extreme events. Following any base forecasting model, we can encode its deterministic outputs into a latent space and retrieve multiple codebook entries to generate probabilistic outputs. Then BeamVQ extends the beam search from discrete spaces to the continuous state spaces in this field. We can further employ domain-specific metrics (e.g., Critical Success Index for extreme events) to filter out the top-k candidates and develop the new self-ensemble strategy by combining the high-quality candidates. The self-ensemble can not only improve the inference quality and robustness but also iteratively augment the training datasets during continuous self-training. Consequently, BeamVQ realizes the exploration of rare but critical phenomena beyond the original dataset. Comprehensive experiments on different benchmarks and backbones show that BeamVQ consistently reduces forecasting MSE (up to 39%), enhancing extreme events detection and proving its effectiveness in handling data scarcity.

cs.LG↗

arXiv2025

SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation

The cross-modal 3D retrieval task aims to achieve mutual matching between text descriptions and 3D shapes. This has the potential to enhance the interaction between natural language and the 3D environment, especially within the realms of robotics and embodied artificial intelligence (AI) applications. However, the scarcity and expensiveness of 3D data constrain the performance of existing cross-modal 3D retrieval methods. These methods heavily rely on features derived from the limited number of 3D shapes, resulting in poor generalization ability across diverse scenarios. To address this challenge, we introduce SCA3D, a novel 3D shape and caption online data augmentation method for cross-modal 3D retrieval. Our approach uses the LLaVA model to create a component library, captioning each segmented part of every 3D shape within the dataset. Notably, it facilitates the generation of extensive new 3D-text pairs containing new semantic features. We employ both inter and intra distances to align various components into a new 3D shape, ensuring that the components do not overlap and are closely fitted. Further, text templates are utilized to process the captions of each component and generate new text descriptions. Besides, we use unimodal encoders to extract embeddings for 3D shapes and texts based on the enriched dataset. We then calculate fine-grained cross-modal similarity using Earth Mover's Distance (EMD) and enhance cross-modal matching with contrastive learning, enabling bidirectional retrieval between texts and 3D shapes. Extensive experiments show our SCA3D outperforms previous works on the Text2Shape dataset, raising the Shape-to-Text RR@1 score from 20.03 to 27.22 and the Text-to-Shape RR@1 score from 13.12 to 16.67. Codes can be found in https://github.com/3DAgentWorld/SCA3D.

cs.CV↗

arXiv2025

Multimode fiber based high-dimensional light analyzer

The wavelength and state of polarization (SOP) are fundamental properties of an optical field which are essential for applications in optical communications, imaging and other fields. However, it is challenging for existing spectrometers and polarimeters to measure these parameters simultaneously, resulting in reduced spatial and temporal efficiency. To overcome this limitation, we propose and demonstrate a compact multimode fiber (MMF)-based high-dimensional light analyzer capable of simultaneously performing high-precision measurements of both wavelength and SOP. Core-offset launching is introduced in the MMF to reshuffle the mode coupling. A neural network named WP-Net has been designed dedicated to wavelength and SOP synchronization measurements. Physics-informed loss function based on optical prior knowledge is used to optimize the learning process. These advancements have enhanced the sensitivity, achieving a wavelength resolution of 0.045 pm and an SOP resolution of 0.0088.

physics.optics↗

arXiv2025

Weighted Low-rank Approximation via Stochastic Gradient Descent on Manifolds

We solve a regularized weighted low-rank approximation problem by a stochastic gradient descent on a manifold. To guarantee the convergence of our stochastic gradient descent, we establish a convergence theorem on manifolds for retraction-based stochastic gradient descents admitting confinements. On sample data from the Netflix Prize training dataset, our algorithm outperforms the existing stochastic gradient descent on Euclidean spaces. We also compare the accelerated line search on this manifold to the existing accelerated line search on Euclidean spaces.

math.OC↗

arXiv2025

Arrival flow profile estimation and predication for urban arterials using license plate recognition data

Arrival flow profiles enable precise assessment of urban arterial dynamics, aiding signal control optimization. License Plate Recognition (LPR) data, with its comprehensive coverage and event-based detection, is promising for reconstructing arrival flow profiles. This paper introduces an arrival flow profile estimation and prediction method for urban arterials using LPR data. Unlike conventional methods that assume traffic homogeneity and overlook detailed traffic wave features and signal timing impacts, our approach employs a time partition algorithm and platoon dispersion model to calculate arrival flow, considering traffic variations and driving behaviors using only boundary data. Shockwave theory quantifies the piecewise function between arrival flow and profile. We derive the relationship between arrival flow profiles and traffic dissipation at downstream intersections, enabling recursive calculations for all intersections. This approach allows prediction of arrival flow profiles under any signal timing schemes. Validation through simulation and empirical cases demonstrates promising performance and robustness under various conditions.

physics.soc-ph↗

arXiv2025

Continuum theory of electrostatic-elastic coupling interactions in colloidal crystals

A mobile Coulomb gas permeating a fixed background crystalline lattice of charged colloidal crystals is subject to an electrostatic-elastic coupling, which we study on the continuum level by introducing a minimal coupling between electrostatic and displacement fields. We derive linearized, Debye-Hückel-like mean-field equations that can be analytically solved, incorporating the minimal coupling between electrostatic and displacement fields leading to an additional effective attractive interaction between mobile charges that depends in general on the strength of the coupling between the electrostatic and displacement fields. By analyzing the Gaussian fluctuations around the mean-field solution we also identify and quantify the region of its stability in terms of the electrostatic-elastic screening length. This detailed continuum theory incorporating the standard lattice elasticity and electrostatics of mobile charges provides a baseline to investigate the electrostatic-elastic coupling for microscopic models in colloid science and materials science.

cond-mat.soft↗

arXiv2025

Dense Object Detection Based on De-homogenized Queries

Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as non-maximum suppression (NMS), often produce many repetitive predictions or missed detections in dense scenarios, which is a common problem faced by NMS-based algorithms. Through the end-to-end DETR (DEtection TRansformer), as a type of detector that can incorporate the post-processing de-duplication capability of NMS, etc., into the network, we found that homogeneous queries in the query-based detector lead to a reduction in the de-duplication capability of the network and the learning efficiency of the encoder, resulting in duplicate prediction and missed detection problems. To solve this problem, we propose learnable differentiated encoding to de-homogenize the queries, and at the same time, queries can communicate with each other via differentiated encoding information, replacing the previous self-attention among the queries. In addition, we used joint loss on the output of the encoder that considered both location and confidence prediction to give a higher-quality initialization for queries. Without cumbersome decoder stacking and guaranteeing accuracy, our proposed end-to-end detection framework was more concise and reduced the number of parameters by about 8% compared to deformable DETR. Our method achieved excellent results on the challenging CrowdHuman dataset with 93.6% average precision (AP), 39.2% MR-2, and 84.3% JI. The performance overperformed previous SOTA methods, such as Iter-E2EDet (Progressive End-to-End Object Detection) and MIP (One proposal, Multiple predictions). In addition, our method is more robust in various scenarios with different densities.

cs.CV↗

arXiv2025

Gradient-free variational learning with conditional mixture networks

Balancing computational efficiency with robust predictive performance is crucial in supervised learning, especially for critical applications. Standard deep learning models, while accurate and scalable, often lack probabilistic features like calibrated predictions and uncertainty quantification. Bayesian methods address these issues but can be computationally expensive as model and data complexity increase. Previous work shows that fast variational methods can reduce the compute requirements of Bayesian methods by eliminating the need for gradient computation or sampling, but are often limited to simple models. We introduce CAVI-CMN, a fast, gradient-free variational method for training conditional mixture networks (CMNs), a probabilistic variant of the mixture-of-experts (MoE) model. CMNs are composed of linear experts and a softmax gating network. By exploiting conditional conjugacy and Pólya-Gamma augmentation, we furnish Gaussian likelihoods for the weights of both the linear layers and the gating network. This enables efficient variational updates using coordinate ascent variational inference (CAVI), avoiding traditional gradient-based optimization. We validate this approach by training two-layer CMNs on standard classification benchmarks from the UCI repository. CAVI-CMN achieves competitive and often superior predictive accuracy compared to maximum likelihood estimation (MLE) with backpropagation, while maintaining competitive runtime and full posterior distributions over all model parameters. Moreover, as input size or the number of experts increases, computation time scales competitively with MLE and other gradient-based solutions like black-box variational inference (BBVI), making CAVI-CMN a promising tool for deep, fast, and gradient-free Bayesian networks.

cs.LG↗

arXiv2025

Finding Quasars Behind the Galactic Plane: Spectroscopic Identifications of ~1300 New Quasars at |b|<=20 degree from LAMOST DR10

Quasars behind the Galactic plane (GPQs) are excellent tracers to probe the chemistry and kinematics of the interstellar/intergalactic medium (ISM/IGM) of the Milky Way along sight lines via absorption line spectroscopy. Moreover, the quasars located at low Galactic latitudes will fill the gap in the spatial distribution of known quasars near the Galactic plane, and can be used to construct an astrometric reference frame for accurate measurements of proper motions (PMs) of stars, and substructures of the Milky Way. We started a survey of background quasars in the low Galactic latitude region since the LAMOST phase II survey in 2017. Quasar candidates have been selected from the optical and infrared photometric data of Pan-STARRS1 and WISE surveys based on their variability and color properties. In this paper, we present a sample of 1982 spectroscopically confirmed GPQs with |b| <= 20 degree based on LAMOST Data Release 10 (DR10). Among them, 1338 are newly discovered. Most GPQs are located around 240<l<90 degree, and the spatial distributions are non-uniform. These GPQs have a magnitude distribution with a peak at i-mag 19.0, and mostly around 18.0-19.5mag. The peak of redshift distributions is around ~1.5, and most GPQs have redshifts between 0.3 and 2.5. Our finding demonstrates the potential discovery space for the GPQs from the spectroscopic surveys and the promising applications for future research.

astro-ph.GA↗

arXiv2025

Coarse-to-Fine Structure-Aware Artistic Style Transfer

Artistic style transfer aims to use a style image and a content image to synthesize a target image that retains the same artistic expression as the style image while preserving the basic content of the content image. Many recently proposed style transfer methods have a common problem; that is, they simply transfer the texture and color of the style image to the global structure of the content image. As a result, the content image has a local structure that is not similar to the local structure of the style image. In this paper, we present an effective method that can be used to transfer style patterns while fusing the local style structure into the local content structure. In our method, dif-ferent levels of coarse stylized features are first reconstructed at low resolution using a Coarse Network, in which style color distribution is roughly transferred, and the content structure is combined with the style structure. Then, the reconstructed features and the content features are adopted to synthesize high-quality structure-aware stylized images with high resolution using a Fine Network with three structural selective fusion (SSF) modules. The effectiveness of our method is demonstrated through the generation of appealing high-quality stylization results and a com-parison with some state-of-the-art style transfer methods.

cs.CV↗

arXiv2025

Multiscale style transfer based on a Laplacian pyramid for traditional Chinese painting

Style transfer is adopted to synthesize appealing stylized images that preserve the structure of a content image but carry the pattern of a style image. Many recently proposed style transfer methods use only western oil paintings as style images to achieve image stylization. As a result, unnatural messy artistic effects are produced in stylized images when using these methods to directly transfer the patterns of traditional Chinese paintings, which are composed of plain colors and abstract objects. Moreover, most of them work only at the original image scale and thus ignore multiscale image information during training. In this paper, we present a novel effective multiscale style transfer method based on Laplacian pyramid decomposition and reconstruction, which can transfer unique patterns of Chinese paintings by learning different image features at different scales. In the first stage, the holistic patterns are transferred at low resolution by adopting a Style Transfer Base Network. Then, the details of the content and style are gradually enhanced at higher resolutions by a Detail Enhancement Network with an edge information selection (EIS) module in the second stage. The effectiveness of our method is demonstrated through the generation of appealing high-quality stylization results and a comparison with some state-of-the-art style transfer methods. Datasets and codes are available at https://github.com/toby-katakuri/LP_StyleTransferNet.

cs.CV↗

arXiv2025

RS-YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images

Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS-YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high-performance remote sensing object detector, we combined the trained model with an open-source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA-v1.5, TGRS-HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets.

cs.CV↗