arXiv subjects

Zhichao Zhang

Publications and source records attributed to Zhichao Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation

Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose PartMotionEdit, a novel fine-grained motion editing framework that operates via part-level semantic modulation. The core of PartMotionEdit is a Part-aware Motion Modulation (PMM) module, which builds upon a predefined five-part body decomposition. PMM dynamically predicts time-varying modulation weights for each body part, enabling precise and interpretable editing of local motions. To guide the training of PMM, we also introduce a part-level similarity curve supervision mechanism enhanced with dual-layer normalization. This mechanism assists PMM in learning semantically consistent and editable distributions across all body parts. Furthermore, we design a Bidirectional Motion Interaction (BMI) module. It leverages bidirectional cross-modal attention to achieve more accurate semantic alignment between textual instructions and motion semantics. Extensive quantitative and qualitative evaluations on a well-known benchmark demonstrate that PartMotionEdit outperforms the state-of-the-art methods.

cs.GR↗

arXiv2025

Dynamic Multiple-Parameter Joint Time-Vertex Fractional Fourier Transform and its Intelligent Filtering Methods

Dynamic graph signal processing provides a principled framework for analyzing time-varying data defined on irregular graph domains. However, existing joint time-vertex transforms such as the joint time-vertex fractional Fourier transform assign only one fractional order to the spatial domain and another one to the temporal domain, thereby restricting their capacity to model the complex and continuously varying dynamics of graph signals. To address this limitation, we propose a novel dynamic multiple-parameter joint time-vertex fractional Fourier transform (DMPJFRFT) framework, which introduces time-varying fractional parameters to achieve adaptive spectral modeling of dynamic graph structures. By assigning distinct fractional orders to each time step, the proposed transform enables dynamic and flexible representation of spatio-temporal signal evolution in the joint time-vertex spectral domain. Theoretical properties of the DMPJFRFT are systematically analyzed, and two filtering approaches: a gradient descent-based method and a neural network-based method, are developed for dynamic signal restoration. Experimental results on dynamic graph and video datasets demonstrate that the proposed framework effectively captures temporal topology variations and achieves superior performance in denoising and deblurring tasks compared with some state-of-the-art graph-based transforms and neural networks.

eess.SP↗

arXiv2025

Two-Dimensional Graph Bi-Fractional Fourier Transform

Graph signal processing (GSP) advances spectral analysis on irregular domains. However, existing two-dimensional graph fractional Fourier transform (2D-GFRFT) employs a single fractional order for both factor graphs, thereby limiting its adaptability to heterogeneous signals. We proposed the two-dimensional graph bi-fractional Fourier transform (2D-GBFRFT), which assigns independent fractional orders to the factor graphs of a Cartesian product while preserving separability. We established invertibility, unitarity, and index additivity, and developed two filtering schemes: a Wiener-style design through grid search and a differentiable framework that jointly optimizes transform orders and diagonal spectral filters. We further introduced a hybrid interpolation with the joint time-vertex fractional Fourier transform (JFRFT), controlled by a tunable parameter that balances the two methods. In the domains of synthetic Cartesian product graph signals, authentic temporal graph datasets, and dynamic image deblurring, 2D-GBFRFT consistently surpasses 2D-GFRFT and enhances JFRFT. Experimental results confirmed the versatility and superior performance of 2D-GBFRFT for filtering in GSP.

eess.SP↗

arXiv2025

Graph Signal Wiener Filtering in the Linear Canonical Domain: Theory and Method Design

The graph linear canonical transform (GLCT)-based filtering methods often optimize transform parameters and filters separately, which results in high computational costs and limited stability. To address this issue, this paper proposes a trainable joint optimization framework that combines GLCT parameters and Wiener filtering into an end-to-end learning process, allowing for synergistic optimization between transform domain construction and filtering operations. The proposed method not only eliminates the cumbersome grid search required by traditional strategies but also significantly enhances the flexibility and training stability of the filtering system. Experimental results on real-world graph data show the proposed method outperforms existing methods in denoising tasks, featuring superior denoising performance, higher robustness and lower computational complexity.

eess.SP↗

arXiv2025

Graph Fractional Hilbert Transform: Theory and Application

The graph Hilbert transform (GHT) is a key tool in constructing analytic signals and extracting envelope and phase information in graph signal processing. However, its utility is limited by confinement to the graph Fourier domain, a fixed phase shift, information loss for real-valued spectral components, and the absence of tunable parameters. The graph fractional Fourier transform introduces domain flexibility through a fractional order parameter $α$ but does not resolve the issues of phase rigidity and information loss. Inspired by the dual-parameter fractional Hilbert transform (FRHT) in classical signal processing, we propose the graph FRHT (GFRHT). The GFRHT incorporates a dual-parameter framework: the fractional order $α$ enables analysis across arbitrary fractional domains, interpolating between vertex and spectral spaces, while the angle parameter $β$ provides adjustable phase shifts and a non-zero real-valued response ($\cosβ$) for real eigenvalues, thereby eliminating information loss. We formally define the GFRHT, establish its core properties, and design a method for graph analytic signal construction, enabling precise envelope extraction and demodulation. Experiments on edge detection, anomaly identification, and speech classification demonstrate that GFRHT outperforms GHT, offering greater flexibility and superior performance in graph signal processing.

eess.SP↗

arXiv2025

JFRFFNet: A Data-Model Co-Driven Graph Signal Denoising Model with Partial Prior Information

Wiener filtering in the joint time-vertex fractional Fourier transform (JFRFT) domain has shown high effectiveness in denoising time-varying graph signals. Traditional filtering models use grid search to determine the transform-order pair and compute filter coefficients, while learnable ones employ gradient-descent strategies to optimize them; both require complete prior information of graph signals. To overcome this shortcoming, this letter proposes a data-model co-driven denoising approach, termed neural-network-aided joint time-vertex fractional Fourier filtering (JFRFFNet), which embeds the JFRFT-domain Wiener filter model into a neural network and updates the transform-order pair and filter coefficients through a data-driven approach. This design enables effective denoising using only partial prior information. Experiments demonstrate that JFRFFNet achieves significant improvements in output signal-to-noise ratio compared with some state-of-the-art methods.

eess.SP↗

arXiv2025

VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results

This paper presents a summary of the VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models (LMMs), hosted as part of the ICCV 2025 Workshop on Visual Quality Assessment. The challenge aims to evaluate and enhance the ability of state-of-the-art LMMs to perform open-ended and detailed reasoning about visual quality differences across multiple images. To this end, the competition introduces a novel benchmark comprising thousands of coarse-to-fine grained visual quality comparison tasks, spanning single images, pairs, and multi-image groups. Each task requires models to provide accurate quality judgments. The competition emphasizes holistic evaluation protocols, including 2AFC-based binary preference and multi-choice questions (MCQs). Around 100 participants submitted entries, with five models demonstrating the emerging capabilities of instruction-tuned LMMs on quality assessment. This challenge marks a significant step toward open-domain visual quality reasoning and comparison and serves as a catalyst for future research on interpretable and human-aligned quality evaluation systems.

cs.CV↗

arXiv2025

A Novel Unified Extended Matrix for Graph Signal Processing: Theory and Application

Graph signal processing has become an essential tool for analyzing data structured on irregular domains. While conventional graph shift operators (GSOs) are effective for certain tasks, they inherently lack flexibility in modeling dependencies between non-adjacent nodes, limiting their ability to represent complex graph structures. To address this limitation, this paper proposes the unified extended matrix (UEM) framework, which integrates the extended-adjacency matrix and the unified graph representation matrix through parametric design, so as to be able to flexibly adapt to different graph structures and reveal more graph signal information. Theoretical analysis of the UEM is conducted, demonstrating positive semi-definiteness and eigenvalue monotonicity under specific conditions. Then, we propose graph Fourier transform based on UEM (UEM-GFT), which can adaptively tune spectral properties to enhance signal processing performance. Experimental results on synthetic and real-world datasets demonstrate that the UEM-GFT outperforms existing GSO-based methods in anomaly detection tasks, achieving superior performance across varying network topologies.

cs.LG↗

arXiv2025

Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition

Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local semantics within images. To address this limita tion, we propose the hierarchical graph feature enhancement (HGFE), a novel framework that integrates graph-based rea soning into CNNs to enhance both structural awareness and feature representation. HGFE builds two complementary levels of graph structures: intra-window graph convolution to cap ture local spatial dependencies and inter-window supernode interactions to model global semantic relationships. Moreover, we introduce an adaptive frequency modulation module that dynamically balances low-frequency and high-frequency signal propagation, preserving critical edge and texture information while mitigating over-smoothing. The proposed HGFE module is lightweight, end-to-end trainable, and can be seamlessly integrated into standard CNN backbone networks. Extensive experiments on CIFAR-100 (classification), PASCAL VOC, and VisDrone (detection), as well as CrackSeg and CarParts (segmentation), validated the effectiveness of the HGFE in improving structural representation and enhancing overall recognition performance.

cs.CV↗

arXiv2025

Graph Chirp Signal and Graph Fractional Vertex-Frequency Energy Distribution

Graph signal processing (GSP) has emerged as a powerful framework for analyzing data on irregular domains. In recent years, many classical techniques in signal processing (SP) have been successfully extended to GSP. Among them, chirp signals play a crucial role in various SP applications. However, graph chirp signals have not been formally defined despite their importance. Here, we define graph chirp signals and establish a comprehensive theoretical framework for their analysis. We propose the graph fractional vertex--frequency energy distribution (GFED), which provides a powerful tool for processing and analyzing graph chirp signals. We introduce the general fractional graph distribution (GFGD), a generalized vertex--frequency distribution, and the reduced interference GFED, which can suppress cross-term interference and enhance signal clarity. Furthermore, we propose a novel method for detecting graph signals through GFED domain filtering, facilitating robust detection and analysis of graph chirp signals in noisy environments. Moreover, this method can be applied to real-world data for denoising more effective than some state-of-the-arts, further demonstrating its practical significance.

eess.SP↗

arXiv2025

Trainable Joint Time-Vertex Fractional Fourier Transform

To address limitations of the graph fractional Fourier transform (GFRFT) Wiener filtering and the traditional joint time-vertex fractional Fourier transform (JFRFT) Wiener filtering, this study proposes a filtering method based on the hyper-differential form of the JFRFT. The gradient backpropagation mechanism is employed to enable the adaptive selection of transform order pair and filter coefficients. First, leveraging the hyper-differential form of the GFRFT and the fractional Fourier transform, the hyper-differential form of the JFRFT is constructed and its properties are analyzed. Second, time-varying graph signals are divided into dynamic graph sequences of equal span along the temporal dimension. A spatiotemporal joint representation is then established through vectorized reorganization, followed by the joint time-vertex Wiener filtering. Furthermore, by rigorously proving the differentiability of the transform orders, both the transform orders and filter coefficients are embedded as learnable parameters within a neural network architecture. Through gradient backpropagation, their synchronized iterative optimization is achieved, constructing a parameters-adaptive learning filtering framework. This method leverages a model-driven approach to learn the optimal transform order pair and filter coefficients. Experimental results indicate that the proposed framework improves the time-varying graph signals denoising performance, while reducing the computational burden of the traditional grid search strategy.

eess.SP↗

arXiv2025

Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric

AI-driven video generation techniques have made significant progress in recent years. However, AI-generated videos (AGVs) involving human activities often exhibit substantial visual and semantic distortions, hindering the practical application of video generation technologies in real-world scenarios. To address this challenge, we conduct a pioneering study on human activity AGV quality assessment, focusing on visual quality evaluation and the identification of semantic distortions. First, we construct the AI-Generated Human activity Video Quality Assessment (Human-AGVQA) dataset, consisting of 6,000 AGVs derived from 15 popular text-to-video (T2V) models using 400 text prompts that describe diverse human activities. We conduct a subjective study to evaluate the human appearance quality, action continuity quality, and overall video quality of AGVs, and identify semantic issues of human body parts. Based on Human-AGVQA, we benchmark the performance of T2V models and analyze their strengths and weaknesses in generating different categories of human activities. Second, we develop an objective evaluation metric, named AI-Generated Human activity Video Quality metric (GHVQ), to automatically analyze the quality of human activity AGVs. GHVQ systematically extracts human-focused quality features, AI-generated content-aware quality features, and temporal continuity features, making it a comprehensive and explainable quality metric for human activity AGVs. The extensive experimental results show that GHVQ outperforms existing quality metrics on the Human-AGVQA dataset by a large margin, demonstrating its efficacy in assessing the quality of human activity AGVs. The Human-AGVQA dataset and GHVQ metric will be released at https://github.com/zczhang-sjtu/GHVQ.git.

cs.CV↗

arXiv2025

NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment

This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. The aim of this challenge is to address the fine-grained quality assessment of text-to-image generation models. This challenge evaluates text-to-image models from two aspects: image-text alignment and image structural distortion detection, and is divided into the alignment track and the structural track. The alignment track uses the EvalMuse-40K, which contains around 40K AI-Generated Images (AIGIs) generated by 20 popular generative models. The alignment track has a total of 371 registered participants. A total of 1,883 submissions are received in the development phase, and 507 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. The structure track uses the EvalMuse-Structure, which contains 10,000 AI-Generated Images (AIGIs) with corresponding structural distortion mask. A total of 211 participants have registered in the structure track. A total of 1155 submissions are received in the development phase, and 487 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Almost all methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on T2I model quality assessment.

cs.CV↗

arXiv2025

RBM-Based Simulated Quantum Annealing for Graph Isomorphism Problems

The graph isomorphism problem remains a fundamental challenge in computer science, driving the search for efficient decision algorithms. Due to its ambiguous computational complexity, heuristic approaches such as simulated annealing are frequently used, achieving high solution probabilities while avoiding exhaustive enumeration. However, traditional simulated annealing usually struggles with low sampling efficiency and reduced solution-finding probability in complex or large graph problems. In this study, we integrate the principles of quantum technology to address the graph isomorphism problem. By mapping the solution space to a quantum many-body system, we developed a parameterized model for variational simulated annealing. This approach emphasizes the regions of the solution space that are most likely to contain the optimal solution, thereby enhancing the search accuracy.Artificial neural networks were utilized to parameterize the quantum many-body system, leveraging their capacity for efficient function approximation to perform accurate sampling in the intricate energy landscapes of large graph problems.

quant-ph↗

arXiv2025

AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images

The rapid development of text-to-image (T2I) generation approaches has attracted extensive interest in evaluating the quality of generated images, leading to the development of various quality assessment methods for general-purpose T2I outputs. However, existing image quality assessment (IQA) methods are limited to providing global quality scores, failing to deliver fine-grained perceptual evaluations for structurally complex subjects like humans, which is a critical challenge considering the frequent anatomical and textural distortions in AI-generated human images (AGHIs). To address this gap, we introduce AGHI-QA, the first large-scale benchmark specifically designed for quality assessment of AGHIs. The dataset comprises 4,000 images generated from 400 carefully crafted text prompts using 10 state of-the-art T2I models. We conduct a systematic subjective study to collect multidimensional annotations, including perceptual quality scores, text-image correspondence scores, visible and distorted body part labels. Based on AGHI-QA, we evaluate the strengths and weaknesses of current T2I methods in generating human images from multiple dimensions. Furthermore, we propose AGHI-Assessor, a novel quality metric that integrates the large multimodal model (LMM) with domain-specific human features for precise quality prediction and identification of visible and distorted body parts in AGHIs. Extensive experimental results demonstrate that AGHI-Assessor showcases state-of-the-art performance, significantly outperforming existing IQA methods in multidimensional quality assessment and surpassing leading LMMs in detecting structural distortions in AGHIs.

cs.CV↗

arXiv2025

Symplectic Wigner Distribution in the Linear Canonical Transform Domain: Theory and Application

This paper devotes to combine the chirp basis function transformation and symplectic coordinates transformation to yield a novel Wigner distribution (WD) associated with the linear canonical transform (LCT), named as the symplectic WD in the LCT domain (SWDL). It incorporates the merits of the symplectic WD (SWD) and the WD in the LCT domain (WDL), achieving stronger capability in the linear frequency-modulated (LFM) signal frequency rate feature extraction while maintaining the same level of computational complexity. Some essential properties of the SWDL are derived, including marginal distributions, energy conservations, unique reconstruction, Moyal formula, complex conjugate symmetry, time reversal symmetry, scaling property, time translation property, frequency modulation property, and time translation and frequency modulation property. Heisenberg's uncertainty principles of the SWDL are formulated, giving rise to three kinds of lower bounds attainable respectively by Gaussian enveloped complex exponential signal, Gaussian signal and Gaussian enveloped chirp signal. The optimal symplectic matrices corresponding to the highest time-frequency resolution are generated by solving the lower bound optimization (minimization) problem. The time-frequency resolution of the SWDL is compared with those of the SWD and WDL to demonstrate its superiority in LFM signals time-frequency energy concentration. A synthesis example is also carried out to verify the feasibility and reliability of the theoretical analysis.

eess.SP↗

arXiv2025

Standard Heisenberg's uncertainty principles of Cohen's class time-frequency distribution with specific kernels

Time-frequency concentration and resolution of the Cohen's class time-frequency distribution (CCTFD) has attracted much attention in time-frequency analysis. A variety of uncertainty principles of the CCTFD is therefore derived, including the weak Heisenberg type, the Hardy type, the Nazarov type, and the local type. However, the standard Heisenberg type still remains unresolved. In this study, we address the question of how the standard Heisenberg's uncertainty principle of the CCTFD is affected by fundamental properties. The investigated distribution properties are Parseval's relation and the concise frequency domain definition (i.e., only frequency variables are explicitly found in the tensor product), based on which we confine our attention to the CCTFD with some specific kernels. That is the unit modulus and v-independent time translation, reversal and scaling invariant kernel CCTFD (UMITRSK-CCTFD). We then extend the standard Heisenberg's uncertainty principles of the Wigner distribution to those of the UMITRSK-CCTFD, giving birth to various types of attainable lower bounds on the uncertainty product in the UMITRSK-CCTFD domain. The derived results strengthen the existing weak Heisenberg type and fill gaps in the standard Heisenberg type.

eess.SP↗

arXiv2025

HMCGeo: IP Region Prediction Based on Hierarchical Multi-label Classification

Fine-grained IP geolocation plays a critical role in applications such as location-based services and cybersecurity. Most existing fine-grained IP geolocation methods are regression-based; however, due to noise in the input data, these methods typically encounter kilometer-level prediction errors and provide incorrect region information for users. To address this issue, this paper proposes a novel hierarchical multi-label classification framework for IP region prediction, named HMCGeo. This framework treats IP geolocation as a hierarchical multi-label classification problem and employs residual connection-based feature extraction and attention prediction units to predict the target host region across multiple geographical granularities. Furthermore, we introduce probabilistic classification loss during training, combining it with hierarchical cross-entropy loss to form a composite loss function. This approach optimizes predictions by utilizing hierarchical constraints between regions at different granularities. IP region prediction experiments on the New York, Los Angeles, and Shanghai datasets demonstrate that HMCGeo achieves superior performance across all geographical granularities, significantly outperforming existing IP geolocation methods.

cs.LG↗