arXiv subjects

Xiaoping Zhang

Publications and source records attributed to Xiaoping Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

TMT: Cross-domain Semantic Segmentation with Region-adaptive Transferability Estimation

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention mechanisms. While existing global and patch-level adaptation methods offer some improvements, they overlook the spatially varying transferability inherent in different image regions. To address this, we propose the Transferable Mask Transformer (TMT), a region-adaptive framework designed to enhance cross-domain representation learning through transferability guidance. First, we dynamically partition the image into coherent regions, grouped by structural and semantic similarity, and estimates their domain transferability at a localized level. Then, we incorporate region-level transferability maps directly into the self-attention mechanism of ViTs, allowing the model to adaptively focus attention on areas with lower transferability and higher semantic uncertainty. Extensive experiments across 20 diverse cross-domain settings demonstrate that TMT not only mitigates the performance degradation typically associated with domain shift but also consistently outperforms existing approaches.

cs.CV↗

arXiv2025

A Unified Probabilistic Framework for Dictionary Learning with Parsimonious Activation

Dictionary learning is traditionally formulated as an $L_1$-regularized signal reconstruction problem. While recent developments have incorporated discriminative, hierarchical, or generative structures, most approaches rely on encouraging representation sparsity over individual samples that overlook how atoms are shared across samples, resulting in redundant and sub-optimal dictionaries. We introduce a parsimony promoting regularizer based on the row-wise $L_\infty$ norm of the coefficient matrix. This additional penalty encourages entire rows of the coefficient matrix to vanish, thereby reducing the number of dictionary atoms activated across the dataset. We derive the formulation from a probabilistic model with Beta-Bernoulli priors, which provides a Bayesian interpretation linking the regularization parameters to prior distributions. We further establish theoretical calculation for optimal hyperparameter selection and connect our formulation to both Minimum Description Length, Bayesian model selection and pathlet learning. Extensive experiments on benchmark datasets demonstrate that our method achieves substantially improved reconstruction quality (with a 20\% reduction in RMSE) and enhanced representation sparsity, utilizing fewer than one-tenth of the available dictionary atoms, while empirically validating our theoretical analysis.

cs.LG↗

arXiv2025

DSAT-HD: Dual-Stream Adaptive Transformer with Hybrid Decomposition for Multivariate Time Series Forecasting

Time series forecasting is crucial for various applications, such as weather, traffic, electricity, and energy predictions. Currently, common time series forecasting methods are based on Transformers. However, existing approaches primarily model limited time series or fixed scales, making it more challenging to capture diverse features cross different ranges. Additionally, traditional methods like STL for complex seasonality-trend decomposition require pre-specified seasonal periods and typically handle only single, fixed seasonality. We propose the Hybrid Decomposition Dual-Stream Adaptive Transformer (DSAT-HD), which integrates three key innovations to address the limitations of existing methods: 1) A hybrid decomposition mechanism combining EMA and Fourier decomposition with RevIN normalization, dynamically balancing seasonal and trend components through noise Top-k gating; 2) A multi-scale adaptive pathway leveraging a sparse allocator to route features to four parallel Transformer layers, followed by feature merging via a sparse combiner, enhanced by hybrid attention combining local CNNs and global interactions; 3) A dual-stream residual learning framework where CNN and MLP branches separately process seasonal and trend components, coordinated by a balanced loss function minimizing expert collaboration variance. Extensive experiments on nine datasets demonstrate that DSAT-HD outperforms existing methods overall and achieves state-of-the-art performance on some datasets. Notably, it also exhibits stronger generalization capabilities across various transfer scenarios.

cs.LG↗

arXiv2025

VideoGuard: Protecting Video Content from Unauthorized Editing

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these capabilities for misleading activities. Although existing research has attempted to shield photographic images from being manipulated by generative models, there remains a significant disparity in the protection offered to video content editing. To bridge the gap, we propose a protection method named VideoGuard, which can effectively protect videos from unauthorized malicious editing. This protection is achieved through the subtle introduction of nearly unnoticeable perturbations that interfere with the functioning of the intended generative diffusion models. Due to the redundancy between video frames, and inter-frame attention mechanism in video diffusion models, simply applying image-based protection methods separately to every video frame can not shield video from unauthorized editing. To tackle the above challenge, we adopt joint frame optimization, treating all video frames as an optimization entity. Furthermore, we extract video motion information and fuse it into optimization objectives. Thus, these alterations can effectively force the models to produce outputs that are implausible and inconsistent. We provide a pipeline to optimize this perturbation. Finally, we use both objective metrics and subjective metrics to demonstrate the efficacy of our method, and the results show that the protection performance of VideoGuard is superior to all the baseline methods.

cs.CV↗

arXiv2025

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a range of multimodal tasks. However, their inference efficiency is constrained by the large number of visual tokens processed during decoding. To address this challenge, we propose Per-Layer Per-Head Vision Token Pruning (PLPHP), a two-level fine-grained pruning method including Layer-Level Retention Rate Allocation and Head-Level Vision Token Pruning. Motivated by the Vision Token Re-attention phenomenon across decoder layers, we dynamically adjust token retention rates layer by layer. Layers that exhibit stronger attention to visual information preserve more vision tokens, while layers with lower vision attention are aggressively pruned. Furthermore, PLPHP applies pruning at the attention head level, enabling different heads within the same layer to independently retain critical context. Experiments on multiple benchmarks demonstrate that PLPHP delivers an 18% faster decoding speed and reduces the Key-Value Cache (KV Cache) size by over 50%, all at the cost of 0.46% average performance drop, while also achieving notable performance improvements in multi-image tasks. These results highlight the effectiveness of fine-grained token pruning and contribute to advancing the efficiency and scalability of LVLMs. Our source code will be made publicly available.

cs.CV↗

arXiv2024

Human-Robot Cooperative Piano Playing with Learning-Based Real-Time Music Accompaniment

Recent advances in machine learning have paved the way for the development of musical and entertainment robots. However, human-robot cooperative instrument playing remains a challenge, particularly due to the intricate motor coordination and temporal synchronization. In this paper, we propose a theoretical framework for human-robot cooperative piano playing based on non-verbal cues. First, we present a music improvisation model that employs a recurrent neural network (RNN) to predict appropriate chord progressions based on the human's melodic input. Second, we propose a behavior-adaptive controller to facilitate seamless temporal synchronization, allowing the cobot to generate harmonious acoustics. The collaboration takes into account the bidirectional information flow between the human and robot. We have developed an entropy-based system to assess the quality of cooperation by analyzing the impact of different communication modalities during human-robot collaboration. Experiments demonstrate that our RNN-based improvisation can achieve a 93\% accuracy rate. Meanwhile, with the MPC adaptive controller, the robot could respond to the human teammate in homophony performances with real-time accompaniment. Our designed framework has been validated to be effective in allowing humans and robots to work collaboratively in the artistic piano-playing task.

cs.RO↗

arXiv2024

Unveiling Mass Transfer in Solar Flares: Insights from Elemental Abundance Evolutions Observed by Chang'E-2 Solar X-ray Monitor

Understanding how elemental abundances evolve during solar flares helps shed light on the mass and energy transfer between different solar atmospheric layers. However, prior studies have mostly concentrated on averaged abundances or specific flare phases, leaving a gap in exploring the comprehensive observations throughout the entire flare process. Consequently, investigations into this area are relatively scarce. Exploiting the Solar X-ray Monitor data obtained from the Chang'E-2 lunar orbiter, we present two comprehensive soft X-ray spectroscopic observations of flares in active regions, AR 11149 and 11158, demonstrating elemental abundance evolutions under different conditions. Our findings unveil the inverse first ionization potential (IFIP) effect during flares for Fe for the first time, and reaffirm its existence for Si. Additionally, we observed a rare depletion of elemental abundances, marking the second IFIP effect in flare decay phases. Our study offers a CSHKP model-based interpretation to elucidate the formation of both the FIP and IFIP effects in flare dynamics, with the inertia effect being incorporated into the ponderomotive force fractionation model.

astro-ph.SR↗

arXiv2023

Audio-Visual Quality Assessment for User Generated Content: Database and Method

With the explosive increase of User Generated Content (UGC), UGC video quality assessment (VQA) becomes more and more important for improving users' Quality of Experience (QoE). However, most existing UGC VQA studies only focus on the visual distortions of videos, ignoring that the user's QoE also depends on the accompanying audio signals. In this paper, we conduct the first study to address the problem of UGC audio and video quality assessment (AVQA). Specifically, we construct the first UGC AVQA database named the SJTU-UAV database, which includes 520 in-the-wild UGC audio and video (A/V) sequences, and conduct a user study to obtain the mean opinion scores of the A/V sequences. The content of the SJTU-UAV database is then analyzed from both the audio and video aspects to show the database characteristics. We also design a family of AVQA models, which fuse the popular VQA methods and audio features via support vector regressor (SVR). We validate the effectiveness of the proposed models on the three databases. The experimental results show that with the help of audio signals, the VQA models can evaluate the perceptual quality more accurately. The database will be released to facilitate further research.

eess.IV↗

arXiv2023

Deep surrogate model for learning Green's function associated with linear reaction-diffusion operator

In this paper, we present a deep surrogate model for learning the Green's function associated with the reaction-diffusion operator in rectangular domain. The U-Net architecture is utilized to effectively capture the mapping from source to solution of the target partial differential equations (PDEs). To enable efficient training of the model without relying on labeled data, we propose a novel loss function that draws inspiration from traditional numerical methods used for solving PDEs. Furthermore, a hard encoding mechanism is employed to ensure that the predicted Green's function is perfectly matched with the boundary conditions. Based on the learned Green's function from the trained deep surrogate model, a fast solver is developed to solve the corresponding PDEs with different sources and boundary conditions. Various numerical examples are also provided to demonstrate the effectiveness of the proposed model.

math.NA↗

arXiv2023

Pi-ViMo: Physiology-inspired Robust Vital Sign Monitoring using mmWave Radars

Continuous monitoring of human vital signs using non-contact mmWave radars is attractive due to their ability to penetrate garments and operate under different lighting conditions. Unfortunately, most prior research requires subjects to stay at a fixed distance from radar sensors and to remain still during monitoring. These restrictions limit the applications of radar vital sign monitoring in real life scenarios. In this paper, we address these limitations and present "Pi-ViMo", a non-contact Physiology-inspired Robust Vital Sign Monitoring system, using mmWave radars. We first derive a multi-scattering point model for the human body, and introduce a coherent combining of multiple scatterings to enhance the quality of estimated chest-wall movements. It enables vital sign estimations of subjects at any location in a radar's field of view. We then propose a template matching method to extract human vital signs by adopting physical models of respiration and cardiac activities. The proposed method is capable to separate respiration and heartbeat in the presence of micro-level random body movements (RBM) when a subject is at any location within the field of view of a radar. Experiments in a radar testbed show average respiration rate errors of 6% and heart rate errors of 11.9% for the stationary subjects and average errors of 13.5% for respiration rate and 13.6% for heart rate for subjects under different RBMs.

eess.SP↗

arXiv2022

Learning Green's Functions of Linear Reaction-Diffusion Equations with Application to Fast Numerical Solver

Partial differential equations are often used to model various physical phenomena, such as heat diffusion, wave propagation, fluid dynamics, elasticity, electrodynamics and image processing, and many analytic approaches or traditional numerical methods have been developed and widely used for their solutions. Inspired by rapidly growing impact of deep learning on scientific and engineering research, in this paper we propose a novel neural network, GF-Net, for learning the Green's functions of linear reaction-diffusion equations in an unsupervised fashion. The proposed method overcomes the challenges for finding the Green's functions of the equations on arbitrary domains by utilizing physics-informed approach and the symmetry of the Green's function. As a consequence, it particularly leads to an efficient way for solving the target equations under different boundary conditions and sources. We also demonstrate the effectiveness of the proposed approach by experiments in square, annular and L-shape domains.

cs.LG↗

arXiv2022

First report of a solar energetic particle event observed by China's Tianwen-1 mission in transit to Mars

Solar energetic particles (SEPs) associated with flares and/or coronal mass ejection (CME)-driven shocks can impose acute radiation hazards to space explorations. To measure energetic particles in near-Mars space, the Mars Energetic Particle Analyzer (MEPA) instrument onboard China's Tianwen-1 (TW-1) mission was designed. Here, we report the first MEPA measurements of the widespread SEP event occurring on 29 November 2020 when TW-1 was in transit to Mars. This event occurred when TW-1 and Earth were magnetically well connected, known as the Hohmann-Parker effect, thus offering a rare opportunity to understand the underlying particle acceleration and transport process. Measurements from TW-1 and near-Earth spacecraft show similar double-power-law spectra and a radial dependence of the SEP peak intensities. Moreover, the decay phases of the time-intensity profiles at different locations clearly show the reservoir effect. We conclude that the double-power-law spectrum is likely generated at the acceleration site, and that a small but finite cross-field diffusion is crucial to understand the formation of the SEP reservoir phenomenon. These results provide insight into particle acceleration and transport associated with CME-driven shocks, which may contribute to the improvement of relevant physical models.

astro-ph.SR↗

arXiv2022

Experiments on the Electrostatic Transport of Charged Anorthite Particles under Electron Beam Irradiation

To reveal the effect of secondary electron emission on the charging properties of a surface covered by micron-sized insulating dust particles and the migration characteristics of these particles, for the first time, we used a laser Doppler method to measure the diameters and velocities of micron-sized anorthite particles under electron beam irradiation with an incident energy of 350 eV. Here, anorthite particles are being treated as a proxy for lunar regolith. We experimentally confirm that the vertical transport of anorthite particles is always dominant, although the horizontal transport occurs. In our experiments, some anorthite particles were observed to have large vertical velocities up to 9.74 m~s$^{-1}$ at the measurement point. The upper boundary of the vertical velocities $V_{\rm{z}}$ of these high-speed anorthite particles are well constrained by its diameter $D$, that is, $V_{\rm{z}}^2$ linearly depends on $D^{-2}$. These velocity-diameter data provide strong constraints on the dust charging and transportation mechanisms. The shared charge model could not explain the observed velocity-diameter data. Both the isolated charge model and patched charge model appear to require a large dust charging potential of $-$350 to $-$78 V to reproduce the observed data. The micro-structures of the dusty surface may play an important role in producing this charging potential and in understanding the pulse migration phenomenon observed in our experiment. The presented results and analysis in this paper are helpful for understanding the dust charging and electrostatic transport mechanisms in airless celestial bodies such as the Moon and asteroids in various plasma conditions.

astro-ph.EP↗

arXiv2021

Comparison of Anomalous and Galactic Cosmic Ray Oxygen at 1 au during 1997-2020

Using quiet-time measurements of element oxygen within the energy range 7.3--237.9 MeV nuc$^{-1}$ from the ACE spacecraft at 1 au, we compare the energy spectra and intensities of anomalous and Galactic cosmic rays (ACRs and GCRs, respectively) during 1997--2020. Our analysis shows that the transition from ACR-dominated spectrum to GCR-dominated spectrum occurs at energies $\sim$15 to $\sim$35 MeV nuc$^{-1}$, and the transition energy $E_t$ is found to be well anticorrelated with varying solar activity. This is the first study of ACR-GCR transition energy dependence on the solar cycle variation. At energies below $E_t$, the index of the power-law ACR-dominated spectrum ($γ_1$) ranges from -2.0 to -0.5, whereas the GCR-dominated spectrum has a power-law index ($γ_2$) changing from 0.3 to 0.8 at energies ranging from $E_t$ to 237.9 MeV nuc$^{-1}$. Both $γ_1$ and $γ_2$ are positively correlated with solar activity. In addition, during the solar cycle 24/25 minimum period, the peak GCR intensity observed by ACE spacecraft is about 8\% above its 2009 value, setting a new record since the space age, while the peak ACR intensity is almost similar to that of the previous two solar cycles with the same pattern of solar magnetic polarity, indicating a different modulation mechanism between ACRs and GCRs.

astro-ph.HE↗

arXiv2021

Variations of the Galactic Cosmic Rays in the Recent Solar Cycles

In this paper, we study the galactic cosmic ray (GCR) variations over the solar cycles 23 and 24, with measurements from the NASA's ACE/CRIS instrument and the ground-based neutron monitors (NMs). The results show that the maximum GCR intensities of heavy nuclei (nuclear charge 5-28, 50-500 MeV/nuc) at 1 AU during the solar minimum in 2019-2020 break their previous records, exceeding those recorded in 1997 and 2009 by ~25% and ~6%, respectively, and are at the highest levels since the space age. However, the peak NM count rates are lower than those in late 2009. The difference between GCR intensities and NM count rates still remains to be explained. Furthermore, we find that the GCR modulation environment during the solar minimum P24/25 are significantly different from previous solar minima in several aspects, including remarkably low sunspot numbers, extremely low inclination of the heliospheric current sheet, rare coronal mass ejections, weak interplanetary magnetic field and turbulence. These changes are conducive to reduce the level of solar modulation, providing a plausible explanation for the record-breaking GCR intensities in interplanetary space.

astro-ph.SR↗

arXiv2021

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition

Gait, i.e., the movement pattern of human limbs during locomotion, is a promising biometric for the identification of persons. Despite significant improvement in gait recognition with deep learning, existing studies still neglect a more practical but challenging scenario -- unsupervised cross-domain gait recognition which aims to learn a model on a labeled dataset then adapts it to an unlabeled dataset. Due to the domain shift and class gap, directly applying a model trained on one source dataset to other target datasets usually obtains very poor results. Therefore, this paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition. To learn effective prior knowledge for gait representation, we first adopt a backbone network pre-trained on the labeled source data in a supervised manner. Then we design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space. During training, the class consistency indicator is adopted to select confident neighborhoods of samples based on their entropy measurements. Moreover, we explore a high-entropy-first neighbor selection strategy, which can effectively transfer prior knowledge to the target domain. Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.

cs.CV↗

arXiv2018

Interactive Binary Image Segmentation with Edge Preservation

Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition. In this paper, we propose a novel interactive binary image segmentation method based on the Markov Random Field (MRF) framework and the fast bilateral solver (FBS) technique. Specifically, we employ the geodesic distance component to build the unary term. To ensure both computation efficiency and effective responsiveness for interactive segmentation, superpixels are used in computing geodesic distances instead of pixels. Furthermore, we take a bilateral affinity approach for the pairwise term in order to preserve edge information and denoise. Through the alternating direction strategy, the MRF energy minimization problem is divided into two subproblems, which then can be easily solved by steepest gradient descent (SGD) and FBS respectively. Experimental results on the VGG interactive image segmentation dataset show that the proposed algorithm outperforms several state-of-the-art ones, and in particular, it can achieve satisfactory edge-smooth segmentation results even when the foreground and background color appearances are quite indistinctive.

cs.CV↗

arXiv2015

Global Mg/Si and Al/Si Distributions on Lunar Surface Derived from Chang'E-2 X-ray Spectrometer

X-ray fluorescence remote sensing technique plays a significant role in the chemical compositions research of the Moon. Here we describe the data analysis method for China's Chang'E-2 X-ray spectrometer (CE2XRS) in detail and present the preliminary results: the first global Mg/Si and Al/Si maps on the lunar surface. Our results show that the distributions of Mg/Si and Al/Si correlate well with the terrains of the Moon. The higher Mg/Si ratio corresponding to the mare regions while the lower value corresponding to the highland terrains. The map of Al/Si ratio shows a reverse relationship with the map of Mg/Si ratio.

astro-ph.EP↗