arXiv subjects

Wan Zhang

Publications and source records attributed to Wan Zhang.

8 recordsLinked to original sources

arXiv2026

YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification

Referring multi-object tracking (RMOT) aims to track every instance in a video that matches a given language expression. Despite the recent integration of multimodal large language models (MLLMs) to enhance generalization, existing methods predominantly relegate them to the role of caption generators, necessitating external modules for final decision-making. This paradigm not only introduces extra latency but also severely underutilizes the inherent vision-language alignment capabilities of MLLMs. To address these limitations, we propose YesTrack, a novel two-stage RMOT method that reformulates referring as a discriminative task, directly leveraging MLLMs for Yes/No verification without explicit text generation. To further enhance the reliability and efficiency of this MLLM-based verification, we introduce two lightweight temporal consistency constraints: Temporal Confidence Prior (TCP) and Temporal Reference Propagation (TRP). We further validate the generality of this discriminative paradigm by proposing YesTrack-MOT, a straightforward yet highly effective instantiation for generic multi-object tracking (MOT). Experiments on Refer-KITTI and Refer-KITTI-V2 show that YesTrack significantly outperforms existing state-of-the-art methods while maintaining high efficiency, even when implemented with the smallest variant of Qwen3-VL. Code is released at https://github.com/ggbondrighthere24/YesTrack.

cs.CV↗

arXiv2026

Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting

Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific information. We introduce Hopformer (Homogeneity-Pursuit Transformer), a two-stage framework that addresses this challenge. In the first stage, we perform a Sparsity Pattern Aggregation (SPA) scheme extracting a common low-variance trend that incorporates the covariates. This acts as a homogenization layer. In the second stage, a LoRA-fine-tuned Transformer models the remaining complex dependencies in the residual. Our method is theoretically grounded. We prove that SPA achieves a near-optimal bias-variance trade-off via an oracle inequality. We also provide generalization bounds for the second stage under dependent time series data. Hopformer sets a new state of the art, improving MASE by an average of 6.56% across synthetic and real-world forecasting benchmarks.

stat.ML↗

arXiv2026

Status report towards implementation of a Compton polarimeter at BEPCII

Precision beam polarization measurements based on Compton polarimeters are essential for the physics program of future high-energy colliders. In order to prepare for these and to extend the scope of physics measurements of the BESIII experiment at the BEPCII, a diagnostic of electron beam transverse polarization at BEPCII is of interest. The design and status report of the commissioning, until July 2025, of this device is reported in this paper. We report unambiguous observation of Compton interaction, discuss current limitations of the experimental setup and draw prospects for improvements and actual measurement of electron beam polarization in the near future.

physics.acc-ph↗

arXiv2025

Basis Choices for Frequency Domain Statistical Independence Tests and Algorithms for Algebraic Relation Extraction

In this paper, we explore how different selections of basis functions impact the efficacy of frequency domain techniques in statistical independence tests, and study different algorithms for extracting low-dimensional algebraic relations from dependent data. We examine a range of complete orthonormal bases functions including the Legendre polynomials, Fourier series, Walsh functions, and standard and nonstandard Haar wavelet bases. We utilize fast transformation algorithms to efficiently transform physical domain data to frequency domain coefficients. The main focuses of this paper are the effectiveness of different basis selections in detecting data dependency using frequency domain data, e.g., whether varying basis choices significantly influence statistical power loss for small data with large noise; and on the stability of different optimization formulations for finding proper algebraic relations when data are dependent. We present numerical results to demonstrate the effectiveness of frequency domain-based statistical analysis methods and provide guidance for selecting the proper basis and algorithm to detect a particular type of relations.

math.NA↗

arXiv2025

CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection

Memory stability and learning flexibility in continual learning (CL) is a core challenge for cross-scene Hyperspectral Anomaly Detection (HAD) task. Biological neural networks can actively forget history knowledge that conflicts with the learning of new experiences by regulating learning-triggered synaptic expansion and synaptic convergence. Inspired by this phenomenon, we propose a novel Biologically-Inspired Continual Learning Generative Adversarial Network (CL-BioGAN) for augmenting continuous distribution fitting ability for cross-domain HAD task, where Continual Learning Bio-inspired Loss (CL-Bio Loss) and self-attention Generative Adversarial Network (BioGAN) are incorporated to realize forgetting history knowledge as well as involving replay strategy in the proposed BioGAN. Specifically, a novel Bio-Inspired Loss composed with an Active Forgetting Loss (AF Loss) and a CL loss is designed to realize parameters releasing and enhancing between new task and history tasks from a Bayesian perspective. Meanwhile, BioGAN loss with L2-Norm enhances self-attention (SA) to further balance the stability and flexibility for better fitting background distribution for open scenario HAD (OHAD) tasks. Experiment results underscore that the proposed CL-BioGAN can achieve more robust and satisfying accuracy for cross-domain HAD with fewer parameters and computation cost. This dual contribution not only elevates CL performance but also offers new insights into neural adaptation mechanisms in OHAD task.

cs.CV↗

arXiv2022

Pairwise Nonlinear Dependence Analysis of Genomic Data

In The Cancer Genome Atlas (TCGA) data set, there are many interesting nonlinear dependencies between pairs of genes that reveal important relationships and subtypes of cancer. Such genomic data analysis requires a rapid, powerful and interpretable detection process, especially in a high-dimensional environment. We study the nonlinear patterns among the expression of pairs of genes from TCGA using a powerful tool called Binary Expansion Testing. We find many nonlinear patterns, some of which are driven by known cancer subtypes, some of which are novel.

stat.AP↗

arXiv2021

BEAUTY Powered BEAST

We study distribution-free goodness-of-fit tests with the proposed Binary Expansion Approximation of UniformiTY (BEAUTY) approach. This method generalizes the renowned Euler's formula, and approximates the characteristic function of any copula through a linear combination of expectations of binary interactions from marginal binary expansions. This novel theory enables a unification of many important tests of independence via approximations from specific quadratic forms of symmetry statistics, where the deterministic weight matrix characterizes the power properties of each test. To achieve a robust power, we examine test statistics with data-adaptive weights, referred to as the Binary Expansion Adaptive Symmetry Test (BEAST). For any given alternative, we demonstrate that the Neyman-Pearson test can be approximated by an oracle weighted sum of symmetry statistics. The BEAST with this oracle provides a useful benchmark of feasible power. To approach this oracle power, we devise the BEAST through a regularized resampling approximation of the oracle test. The BEAST improves the empirical power of many existing tests against a wide spectrum of common alternatives and delivers a clear interpretation of dependency forms when significant.

stat.ME↗

arXiv2015

Identifying Emotion from Natural Walking

Emotion identification from gait aims to automatically determine persons affective state, it has attracted a great deal of interests and offered immense potential value in action tendency, health care, psychological detection and human-computer(robot) interaction.In this paper, we propose a new method of identifying emotion from natural walking, and analyze the relevance between the traits of walking and affective states. After obtaining the pure acceleration data of wrist and ankle, we set a moving average filter window with different sizes w, then extract 114 features including time-domain, frequency-domain, power and distribution features from each data slice, and run principal component analysis (PCA) to reduce dimension. In experiments, we train SVM, Decision Tree, multilayerperception, Random Tree and Random Forest classification models, and compare the classification accuracy on data of wrist and ankle with respect to different w. The performance of emotion identification on acceleration data of ankle is better than wrist.Comparing different classification models' results, SVM has best accuracy of identifying anger and happy could achieve 90:31% and 89:76% respectively, and identification ratio of anger-happy is 87:10%.The anger-neutral-happy classification reaches 85%-78%-78%.The results show that it is capable of identifying personal emotional states through the gait of walking.

cs.CV↗