arXiv subjects

Yaru Chen

Publications and source records attributed to Yaru Chen.

14 recordsLinked to original sources

arXiv2026

RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers

Audio editing aims to modify specific content in an existing audio clip according to a text instruction or description while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion transformers provide stronger global modeling and multimodal fusion, but existing editing architectures usually adopt a simple stack of diffusion transformer blocks. Applying joint attention over concatenated audio and text tokens in all blocks results in quadratic complexity with respect to token length. To balance editing performance and efficiency, we propose a novel instruction-guided audio editing framework based on rectified flow matching (RFM), named RFM-Editing 2, built on a hybrid two-stage diffusion transformer. The proposed model performs joint attention over audio and text tokens to establish coarse semantic alignment at the low-resolution stage, then switches to alternating joint-attention and cross-attention blocks to refine editing details at the high-resolution stage. This coarse-to-fine strategy enables efficient and accurate instruction-guided audio editing. Experiments show that the proposed framework achieves notable performance gains on challenging editing tasks involving overlapping audio events and complex instructions, while substantially improving editing efficiency.

cs.SD↗

arXiv2026

Cross-Camera Cow Identification via Disentangled Representation Learning

Precise identification of individual cows is a fundamental prerequisite for comprehensive digital management in smart livestock farming. While existing animal identification methods excel in controlled, single-camera settings, they face severe challenges regarding cross-camera generalization. When models trained on source cameras are deployed to new monitoring nodes characterized by divergent illumination, backgrounds, viewpoints, and heterogeneous imaging properties, recognition performance often degrades dramatically. This limits the large-scale application of non-contact technologies in dynamic, real-world farming environments. To address this challenge, this study proposes a cross-camera cow identification framework based on disentangled representation learning. This framework leverages the Subspace Identifiability Guarantee (SIG) theory in the context of bovine visual recognition. By modeling the underlying physical data generation process, we designed a principle-driven feature disentanglement module that decomposes observed images into multiple orthogonal latent subspaces. This mechanism effectively isolates stable, identity-related biometric features that remain invariant across cameras, thereby substantially improving generalization to unseen cameras. We constructed a high-quality dataset spanning five distinct camera nodes, covering heterogeneous acquisition devices and complex variations in lighting and angles. Extensive experiments across seven cross-camera tasks demonstrate that the proposed method achieves an average accuracy of 86.0%, significantly outperforming the Source-only Baseline (51.9%) and the strongest cross-camera baseline method (79.8%). This work establishes a subspace-theoretic feature disentanglement framework for collaborative cross-camera cow identification, offering a new paradigm for precise animal monitoring in uncontrolled smart farming environments.

cs.CV↗

arXiv2025

MCVI-SANet: A lightweight semi-supervised model for LAI and SPAD estimation of winter wheat under vegetation index saturation

Vegetation index (VI) saturation during the dense canopy stage and limited ground-truth annotations of winter wheat constrain accurate estimation of LAI and SPAD. Existing VI-based and texture-driven machine learning methods exhibit limited feature expressiveness. In addition, deep learning baselines suffer from domain gaps and high data demands, which restrict their generalization. Therefore, this study proposes the Multi-Channel Vegetation Indices Saturation Aware Net (MCVI-SANet), a lightweight semi-supervised vision model. The model incorporates a newly designed Vegetation Index Saturation-Aware Block (VI-SABlock) for adaptive channel-spatial feature enhancement. It also integrates a VICReg-based semi-supervised strategy to further improve generalization. Datasets were partitioned using a vegetation height-informed strategy to maintain representativeness across growth stages. Experiments over 10 repeated runs demonstrate that MCVI-SANet achieves state-of-the-art accuracy. The model attains an average R2 of 0.8123 and RMSE of 0.4796 for LAI, and an average R2 of 0.6846 and RMSE of 2.4222 for SPAD. This performance surpasses the best-performing baselines, with improvements of 8.95% in average LAI R2 and 8.17% in average SPAD R2. Moreover, MCVI-SANet maintains high inference speed with only 0.10M parameters. Overall, the integration of semi-supervised learning with agronomic priors provides a promising approach for enhancing remote sensing-based precision agriculture.

cs.CV↗

arXiv2025

CT-CLIP: A Multi-modal Fusion Framework for Robust Apple Leaf Disease Recognition in Complex Environments

In complex orchard environments, the phenotypic heterogeneity of different apple leaf diseases, characterized by significant variation among lesions, poses a challenge to traditional multi-scale feature fusion methods. These methods only integrate multi-layer features extracted by convolutional neural networks (CNNs) and fail to adequately account for the relationships between local and global features. Therefore, this study proposes a multi-branch recognition framework named CNN-Transformer-CLIP (CT-CLIP). The framework synergistically employs a CNN to extract local lesion detail features and a Vision Transformer to capture global structural relationships. An Adaptive Feature Fusion Module (AFFM) then dynamically fuses these features, achieving optimal coupling of local and global information and effectively addressing the diversity in lesion morphology and distribution. Additionally, to mitigate interference from complex backgrounds and significantly enhance recognition accuracy under few-shot conditions, this study proposes a multimodal image-text learning approach. By leveraging pre-trained CLIP weights, it achieves deep alignment between visual features and disease semantic descriptions. Experimental results show that CT-CLIP achieves accuracies of 97.38% and 96.12% on a publicly available apple disease and a self-built dataset, outperforming several baseline methods. The proposed CT-CLIP demonstrates strong capabilities in recognizing agricultural diseases, significantly enhances identification accuracy under complex environmental conditions, provides an innovative and practical solution for automated disease recognition in agricultural applications.

cs.CV↗

arXiv2025

RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing

Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest, thus demanding precise localization and faithful editing according to the text prompt. Existing training-based and zero-shot methods that rely on full-caption or costly optimization often struggle with complex editing or lack practicality. In this work, we propose a novel end-to-end efficient rectified flow matching-based diffusion framework for audio editing, and construct a dataset featuring overlapping multi-event audio to support training and benchmarking in complex scenarios. Experiments show that our model achieves faithful semantic alignment without requiring auxiliary captions or masks, while maintaining competitive editing quality across metrics.

cs.SD↗

arXiv2025

Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing

Weakly-supervised audio-visual video parsing (AVVP) seeks to detect audible, visible, and audio-visual events without temporal annotations. Previous work has emphasized refining global predictions through contrastive or collaborative learning, but neglected stable segment-level supervision and class-aware cross-modal alignment. To address this, we propose two strategies: (1) an exponential moving average (EMA)-guided pseudo supervision framework that generates reliable segment-level masks via adaptive thresholds or top-k selection, offering stable temporal guidance beyond video-level labels; and (2) a class-aware cross-modal agreement (CMA) loss that aligns audio and visual embeddings at reliable segment-class pairs, ensuring consistency across modalities while preserving temporal structure. Evaluations on LLP and UnAV-100 datasets shows that our method achieves state-of-the-art (SOTA) performance across multiple metrics.

cs.CV↗

arXiv2025

TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph

Audio-visual video parsing (AVVP) aims to detect event categories and their temporal boundaries in videos, typically under weak supervision. Existing methods mainly focus on (i) improving temporal modeling using attention-based architectures or (ii) generating richer pseudo-labels to address the absence of frame-level annotations. However, attention-based models often overfit noisy pseudo-labels, leading to cumulative training errors, while pseudo-label generation approaches distribute attention uniformly across frames, weakening temporal localization accuracy. To address these challenges, we propose TEn-CATG, a text-enriched AVVP framework that combines semantic calibration with category-aware temporal reasoning. More specifically, we design a bi-directional text fusion (BiT) module by leveraging audio-visual features as semantic anchors to refine text embeddings, which departs from conventional text-to-feature alignment, thereby mitigating noise and enhancing cross-modal consistency. Furthermore, we introduce the category-aware temporal graph (CATG) module to model temporal relationships by selecting multi-scale temporal neighbors and learning category-specific temporal decay factors, enabling effective event-dependent temporal reasoning. Extensive experiments demonstrate that TEn-CATG achieves state-of-the-art results across multiple evaluation metrics on benchmark datasets LLP and UnAV-100, highlighting its robustness and superior ability to capture complex temporal and semantic dependencies in weakly supervised AVVP tasks.

cs.CV↗

arXiv2025

A Reduced Order Modeling Method with Variable-Separation-Based Domain Decomposition for Parametric Dynamical Systems

This paper proposes a model order reduction method for a class of parametric dynamical systems. Using a temporal Fourier transform, we reformulate these systems into complex-valued elliptic equations in the frequency domain, containing frequency variables and parameters inherited from the original model. To reduce the computational cost of the frequency-variable elliptic equations, we extend the variable-separation-based domain decomposition method to the complex-valued context, resulting in an offline-online procedure for solving the parametric dynamical systems. At the offline stage, separate representations of the solutions for the interface problem and the subproblems are constructed. At the online stage, the solutions of the parametric dynamical systems for new parameter values can be directly derived by utilizing the separate representations and implementing the inverse Fourier transform. The proposed approach is capable of being highly efficient because the online stage is independent of the spatial discretization. Finally, we present three specific instances of parametric dynamical systems to demonstrate the effectiveness of the proposed method.

math.NA↗

arXiv2025

TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing

Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak labels, without mining semantic relationships for different modalities and explicit modeling of event temporal dependencies. This makes it difficult for the model to accurately parse event information for each segment under weak supervision, especially when high similarity between segmental modal features leads to ambiguous event boundaries. Hence, we propose a multimodal optimization framework, TeMTG, that combines text enhancement and multi-hop temporal graph modeling. Specifically, we leverage pre-trained multimodal models to generate modality-specific text embeddings, and fuse them with audio-visual features to enhance the semantic representation of these features. In addition, we introduce a multi-hop temporal graph neural network, which explicitly models the local temporal relationships between segments, capturing the temporal continuity of both short-term and long-range events. Experimental results demonstrate that our proposed method achieves state-of-the-art (SOTA) performance in multiple key indicators in the LLP dataset.

cs.MM↗

arXiv2025

A Dynamical Variable-separation Method for Parameter-dependent Dynamical Systems

This paper proposes a dynamical Variable-separation method for solving parameter-dependent dynamical systems. To achieve this, we establish a dynamical low-rank approximation for the solutions of these dynamical systems by successively enriching each term in the reduced basis functions via a greedy algorithm. This enables us to reformulate the problem to two decoupled evolution equations at each enrichment step, of which one is a parameter-independent partial differential equation and the other one is a parameter-dependent ordinary differential equation. These equations are directly derived from the original dynamical system and the previously separate representation terms. Moreover, the computational process of the proposed method can be split into an offline stage, in which the reduced basis functions are constructed, and an online stage, in which the efficient low-rank representation of the solution is employed. The proposed dynamical Variable-separation method is capable of offering reduced computational complexity and enhanced efficiency compared to many existing low-rank separation techniques. Finally, we present various numerical results for linear/nonlinear parameter-dependent dynamical systems to demonstrate the effectiveness of the proposed method.

math.NA↗

arXiv2024

Formation Under Communication Constraints: Control Performance Meets Channel Capacity

In wireless communication-based formation control systems, the control performance is significantly impacted by the channel capacity of each communication link between agents. This relationship, however, remains under-investigated in the existing studies. To address this gap, the formation control problem of classical second-order multi-agent systems with bounded process noises was considered taking into account the channel capacity. More specifically, the model of communication links between agents is first established, based on a new concept -- guaranteed communication region, which characterizes all possible locations for successful message decoding in the present of control-system uncertainty. Furthermore, we rigorously prove that, the guaranteed communication region does not unboundedly increase with the transmission time, which indicates an important trade-off between the guaranteed communication region and the data rate. The fundamental limits of data rate for any desired accuracy are also obtained. Finally, the integrated design to achieve the desired formation accuracy is proposed, where an estimation-based controller and transmit power control strategy are developed.

cs.MA↗

arXiv2023

Audio-Visual Instance Segmentation

In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual dependencies between these tokens using window-based attention, and tracks sounding objects among the entire video sequences. Extensive experiments reveal that our method performs best on AVISeg, surpassing the existing methods from related tasks. We further conduct the evaluation on several multi-modal large models. Unfortunately, they exhibits subpar performance on instance-level sound source localization and temporal perception. We expect that AVIS will inspire the community towards a more comprehensive multi-modal understanding. Dataset and code is available at https://github.com/ruohaoguo/avis.

cs.CV↗

arXiv2023

CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing

Audio-visual video parsing is the task of categorizing a video at the segment level with weak labels, and predicting them as audible or visible events. Recent methods for this task leverage the attention mechanism to capture the semantic correlations among the whole video across the audio-visual modalities. However, these approaches have overlooked the importance of individual segments within a video and the relationship among them, and tend to rely on a single modality when learning features. In this paper, we propose a novel interactive-enhanced cross-modal perception method~(CM-PIE), which can learn fine-grained features by applying a segment-based attention module. Furthermore, a cross-modal aggregation block is introduced to jointly optimize the semantic representation of audio and visual signals by enhancing inter-modal interactions. The experimental results show that our model offers improved parsing performance on the Look, Listen, and Parse dataset compared to other methods.

cs.CV↗

arXiv2023

Stochastic Domain Decomposition Based on Variable-Separation Method

In this work, we propose a new stochastic domain decomposition method for solving steady-state partial differential equations (PDEs) with random inputs. Based on the efficiency of the Variable-separation (VS) method in simulating stochastic partial differential equations (SPDEs), we extend it to stochastic algebraic systems and apply it to stochastic domain decomposition. The resulting Stochastic Domain Decomposition based on the Variable-separation method (SDD-VS) effectively addresses the ``curse of dimensionality" by leveraging the explicit representation of stochastic functions derived from physical systems. The SDD-VS method aims to obtain a separated representation of the solution for the stochastic interface problem. To enhance efficiency, an offline-online computational decomposition is introduced. In the offline phase, the affine representation of stochastic algebraic systems is obtained through the successive application of the VS method. This serves as a crucial foundation for the SDD-VS method. In the online phase, the interface unknowns of SPDEs are estimated using a quasi-optimal separated representation, enabling the construction of efficient surrogate models for subproblems. The effectiveness of the proposed method is demonstrated via the numerical results of three concrete examples.

math.NA↗