论文检索

Qingyu Shi, Jianzong Wu, Jinbin Bai, Jiangning Zhang, Lu Qi, Yunhai Tong, Xiangtai Li

The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based methods primarily rely on separate spatial and temporal attention mechanisms within the 3D U-Net. In contrast, state-of-the-art video Diffusion Transformers (DiT) models use 3D full attention, which does not explicitly separate temporal and spatial information. Thus, the interaction between spatial and temporal dimensions makes decoupling motion and appearance more challenging for DiT models. In this paper, we propose DeT, a method that adapts DiT models to improve motion transfer ability. Our approach introduces a simple yet effective temporal kernel to smooth DiT features along the temporal dimension, facilitating the decoupling of foreground motion from background appearance. Meanwhile, the temporal kernel effectively captures temporal variations in DiT features, which are closely related to motion. Moreover, we introduce explicit supervision along dense trajectories in the latent feature space to further enhance motion consistency. Additionally, we present MTBench, a general and challenging benchmark for motion transfer. We also introduce a hybrid motion fidelity metric that considers both the global and local motion similarity. Therefore, our work provides a more comprehensive evaluation than previous works. Extensive experiments on MTBench demonstrate that DeT achieves the best trade-off between motion fidelity and edit fidelity.

Zengyu Wan, Wei Zhai, Yang Cao, Zhengjun Zha

Visual 3D motion estimation aims to infer the motion of 2D pixels in 3D space based on visual cues. The key challenge arises from depth variation induced spatio-temporal motion inconsistencies, disrupting the assumptions of local spatial or temporal motion smoothness in previous motion estimation frameworks. In contrast, event cameras offer new possibilities for 3D motion estimation through continuous adaptive pixel-level responses to scene changes. This paper presents EMoTive, a novel event-based framework that models spatio-temporal trajectories via event-guided non-uniform parametric curves, effectively characterizing locally heterogeneous spatio-temporal motion. Specifically, we first introduce Event Kymograph - an event projection method that leverages a continuous temporal projection kernel and decouples spatial observations to encode fine-grained temporal evolution explicitly. For motion representation, we introduce a density-aware adaptation mechanism to fuse spatial and temporal features under event guidance, coupled with a non-uniform rational curve parameterization framework to adaptively model heterogeneous trajectories. The final 3D motion estimation is achieved through multi-temporal sampling of parametric trajectories, yielding optical flow and depth motion fields. To facilitate evaluation, we introduce CarlaEvent3D, a multi-dynamic synthetic dataset for comprehensive validation. Extensive experiments on both this dataset and a real-world benchmark demonstrate the effectiveness of the proposed method.

Sheng Ye, Xin Chen, Yan Zhang, Xianming Lin, Liujuan Cao

Camouflaged object detection (COD) faces unique challenges where target boundaries are intrinsically ambiguous due to their textural similarity to backgrounds. Existing methods relying on single-modality features often produce fragmented predictions due to insufficient boundary constraints.To address this, we propose ESCNet with dynamically coupled edge-texture perception. Our framework introduces three core innovations that work in concert:1) Adaptive Edge-Texture Perceptor (AETP), which creates an edge prediction behaviour where edge and texture information are mutually reinforcing based on the multi-scale features of the image integrated with the global semantic context of the Transformer;2) Dual-Stream Feature Augmentor (DSFA), which dynamically adjusts the kernel sampling position according to the local texture complexity and edge orientation, thus accurately enhancing the feature information at fractal boundaries and amorphous texture locations;3) Multi-Feature Modulation Module (MFMM), which establishes incremental fine-grained improvements for feature calibration and model prediction through enhanced characterisation of edge perception and hierarchical integration of multiple textures. This interconnected system forms a feedback loop where enhanced representations of edge perception enhance model texture prediction and vice versa. Our ESCNet demonstrates significant performance advantages on all three authoritative datasets.

Jiahao Li 0007, Yiqiang Chen 0001, Yunbing Xing, Yang Gu 0001, Xiangyuan Lan

The widespread availability of publicly accessible data on the internet accelerates the progress of deep learning but also raises concerns about unauthorized data usage for training neural networks. Early safeguard methods introduce small, carefully crafted perturbations via surrogate model into data to generate unlearnable data, aiming to prevent models from learning meaningful patterns. However, these methods lack robustness against adversarial training. Later, some works introduce adversarial examples to solve this problem but at the cost of increased overhead of the surrogate model. Recently, Convolution-based unlearnable data (CUDA), a surrogate-free method, has been proposed to address this issue by manually designed class-wise convolution kernels. Despite its success, CUDA suffers from high-frequency detail loss, perturbation hash collisions, and vulnerability to frequency filtering attacks. In this paper, we propose KBS (K-Space Bispectrum Steganography), which embeds class-specific information into the magnitude and phase components of the Fourier domain while preserving visual fidelity under reconstruction constraints. By directly performing steganography in the frequency domain, KBS preserves high-frequency details and avoids hash collisions with compact binary codes, enabling scalability to large-class datasets. Furthermore, KBS resists frequency filtering attacks by embedding perturbations in a way that remains imperceptible in the pixel space. Experimental results on public benchmarks demonstrate that KBS outperforms state-of-the-art methods.

Youchen Xie, Chen Li 0035, Sheng Qiu, Zhi-Jun Wang, Chenhui Li 0001, Yibo Zhao 0001, Zan Gao 0001, Changbo Wang

Dynamic fluid scene reconstruction remains challenging in multimedia applications and digital content creation due to complex motions and changing topology. While Neural Radiance Fields (NeRF) methods are computationally expensive and 3D Gaussian Splatting (3DGS) approaches struggle with fluid phenomena, we propose Fluid-GS, a flexible, efficient end-to-end framework for sparse-view fluid reconstruction that tightly couples density field modeling with velocity estimation via differentiable advection. Our key innovation is a hybrid Lagrangian-Eulerian Gaussian primitive representation that combines the rendering efficiency of 3DGS with physically-accurate fluid motion tracking on Eulerian grid, that enables us to formulate physics-informed constraints derived from Navier-Stokes equations, enforcing temporal coherence and fluid incompressibility. Moreover, to address the inherent challenges of sparse-view reconstruction, we introduce a fluid-specific Gaussian kernel constraint that preserves the spatial characteristics of fluid phenomena, and dynamically adjusts the anisotropic kernel of Gaussian primitives based on local velocity fields, preventing non-physical artifacts. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in both reconstruction quality and computational efficiency.

Shuzhao Xie, Jiahang Liu, Weixiang Zhang, Shijia Ge, Sicheng Pan, Chen Tang, Yunpeng Bai, Cong Zhang 0002, Xiaoyi Fan 0001, Zhi Wang 0001

Recent advances in 3D Gaussian Splatting (3DGS) have greatly improved 3D reconstruction. However, its substantial data size poses a significant challenge for transmission and storage. While many compression techniques have been proposed, they fail to efficiently adapt to fluctuating network bandwidth, leading to resource wastage. We address this issue from the perspective of size-aware compression, where we aim to compress 3DGS to a desired size by quickly searching for suitable hyperparameters. Through a measurement study, we identify key hyperparameters that affect the size - namely, the reserve ratio of Gaussians and bit-width settings for Gaussian attributes. Then, we formulate this hyperparameter optimization problem as a mixed-integer nonlinear programming (MINLP) problem, with the goal of maximizing visual quality while respecting the size budget constraint. To solve the MINLP, we decouple this problem into two parts: discretely sampling the reserve ratio and determining the bit-width settings using integer linear programming (ILP). To solve the ILP more quickly and accurately, we design a quality loss estimator and a calibrated size estimator, as well as implement a CUDA kernel. Extensive experiments on multiple 3DGS variants demonstrate that our method achieves state-of-the-art performance in post-training compression. Furthermore, our method can achieve comparable quality to leading training-required methods after fine-tuning.

Siran Peng, Tianshuo Zhang, Li Gao, Xiangyu Zhu 0001, Haoyuan Zhang, Kai Pang, Zhen Lei 0001

The rapid evolution of deepfake generation technologies necessitates the development of robust face forgery detection algorithms. Recent studies have demonstrated that wavelet analysis can enhance the generalization abilities of forgery detectors. Wavelets effectively capture key facial contours, often slender, fine-grained, and globally distributed, that may conceal subtle forgery artifacts imperceptible in the spatial domain. However, current wavelet-based approaches fail to fully exploit the distinctive properties of wavelet data, resulting in sub-optimal feature extraction and limited performance gains. To address this challenge, we introduce WMamba, a novel wavelet-based feature extractor built upon the Mamba architecture. WMamba maximizes the utility of wavelet information through two key innovations. First, we propose Dynamic Contour Convolution (DCConv), which employs specially crafted deformable kernels to adaptively model slender facial contours. Second, by leveraging the Mamba architecture, our method captures long-range spatial relationships with linear complexity. This efficiency allows for the extraction of fine-grained, globally distributed forgery artifacts from small image patches. Extensive experiments show that WMamba achieves state-of-the-art (SOTA) performance, highlighting its effectiveness in face forgery detection.

Zizhuo Li, Chunbao Su, Fan Fan 0001, Jun Huang 0008, Jiayi Ma 0001

The uproar over two-view correspondence pruning stems from the advent of the ConvNet-style paradigm, which showcases intrinsic proficiency in local context aggregation, tackling the context-agnostic deficiency of MLP-based methods fundamentally and delivering impressive pruning capability. To further unlock the potential of such a paradigm, this perspective study revisits its design decisions and introduces CorrNeXt, a cutting-edge ConvNet-style pruner that incorporates multiple simple but effective improvements. Firstly, we explicitly integrate 2D relative spatial knowledge into motion field modeling, arming the interconversion between unordered sparse motion vectors and ordered image-structured ones with positional awareness. Secondly, considering that existing methods struggle with perceiving global context due to limited receptive field of small-kernel convolution, we devise a context-orthogonal aggregation module that decomposes computationally expensive large-kernel depthwise convolution along channel dimension into a small square kernel, two orthogonal band kernels, and an identity mapping, enjoying large receptive field while maintaining efficiency. Thirdly, we deploy a motion field pyramid architecture that obtains and fuses multi-level motion fields, thereby facilitating the handling of the motion field's discontinuities in case of large scene disparity. Ultimately, we propose an elastic inference strategy that allows the model to introspect the confidence of its predictions at each layer, through which CorrNeXt is endowed with the flexibility of adaptively determining inference termination according to the difficulty of each image pair. Thorough experimentation affirms CorrNeXt's remarkable capabilities.

Yonghyeon Jo, Janghyun Kim, Jinsun Park

Multi-label classification has recently demonstrated promising performance through CLIP-based unsupervised learning. However, existing CLIP-based approaches primarily focus on object-centric features, which limits their ability to capture rich contextual dependencies between objects and their surrounding scenes. In addition, the vision transformer architecture of CLIP exhibits a bias toward the most prominent object, often failing to recognize small or less conspicuous objects precisely. To address these limitations, we propose Background-Aware CLIP-GCN (BAC-GCN), a novel framework that explicitly models class-background interactions and is designed to capture fine-grained visual patterns of small objects effectively. BAC-GCN is composed of three key components: (i) a Similarity Kernel that extracts patch-level local features for each category (i.e., class and background), (ii) a CLIP-GCN that captures relational dependencies between local-global and class-background features, and (iii) a Re-Training for Small Objects (ReSO) strategy that enhances the representation of small and hard-to-learn objects by learning their distinctive visual characteristics. Therefore, our method facilitates a deeper understanding of complex visual contexts, enabling the model to make decisions by leveraging diverse visual cues and their contextual relationships. Extensive experiments demonstrate that BAC-GCN achieves state-of-the-art performance on three benchmark multi-label datasets: VOC07, COCO, and NUS, validating the effectiveness of our approach. The project page is available at: https://github.com/yonghyeonjo46/BAC-GCN.

Jingxing Guo, Guilian Chen, Yimu Sun, Huisi Wu, Jing Qin 0001

Automatic segmentation of echocardiography videos is crucial for computer-aided cardiovascular function assessment in clinical practice. However, it is a challenging task owing to the existence of massive speckle noise, the large shape variations of heart structures between frames, and limited annotations. In this paper, we propose a novel semi-supervised video segmentation model to comprehensively meet these challenges. The proposed approach has two key techniques. First, we propose a dual-stream architecture that processes spatial and temporal features through separate pathways to capture structural details and motion patterns, then enhances spatiotemporal representations by interacting these decomposed features with query features generated from the original input. Second, as speckle noise primarily concentrates in high-frequency regions, we extend the traditional dilated convolution from a frequency perspective, enabling it to adaptively adjust the dilation rate and convolution kernel weights based on high frequency speckle noise information. This enables the network to focus on specific frequency bands, thereby enhancing its ability to capture both low-frequency context and high-frequency local details. Extensive experiments on the CAMUS and EchoNet-Dynamic datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of both accuracy and inference speed. Codes are available at https://github.com/guojx2255/HSCA-SDC.

Yan Chen 0036, Bingbing Jiang 0001, Peng Zhou 0006, Lei Duan, Yuhua Qian, Liang Du 0003

Clustering, a fundamental task in machine learning and data mining, is essential for uncovering patterns by grouping data points with similar characteristics. Traditional methods struggle with nonlinear data structures, but kernel-based approaches alleviate this issue by mapping data to high dimensional spaces. Multiple Kernel Clustering (MKC) further improves clustering by automating kernel selection and integration. However, MKC faces challenges related to kernel graph quality, information loss during relax-and-discretization, neglect of balanced clustering constraints, and the trade-off between high clustering quality and balance. To address these challenges, we introduce Balanced Multiple Kernel Clustering (BMKC). BMKC utilizes local kernel reconstruction and advanced high-order diffusion techniques for comprehensive kernel graph learning. It directly learns a discrete partition matrix using a robust L1-induced local reconstruction criterion, eliminating the two step process. BMKC incorporates an automatic mechanism for trade-off control between clustering and balance, supported by a versatile optimization algorithm accommodating various balance regularization choices. Experimental validation demonstrates the superior performance of MKC on benchmarks data sets, showcasing its effectiveness. The code for our method is publicly available at https://github.com/ChenYan01TYUT/BMKC-ACM-MM-2025.

Hui Liu, Chen Jia, Fan Shi 0001, Xu Cheng 0003, Mengfei Shi, Xia Xie 0003, Shengyong Chen

Achieving pixel-level segmentation with low computational cost using multimodal data remains a key challenge in crack segmentation tasks. Existing methods lack the capability for adaptive perception and efficient interactive fusion of cross-modal features. To address these challenges, we propose a Lightweight Adaptive Cue-Aware Vision Mamba network (LIDAR), which efficiently perceives and integrates morphological and textural cues from different modalities under multimodal crack scenarios, generating clear pixel-level crack segmentation maps. Specifically, LIDAR is composed of a Lightweight Adaptive Cue-Aware Visual State Space module (LacaVSS) and a Lightweight Dual Domain Dynamic Collaborative Fusion module (LD3CF). LacaVSS adaptively models crack cues through the proposed mask-guided Efficient Dynamic Guided Scanning Strategy (EDG-SS), while LD3CF leverages an Adaptive Frequency Domain Perceptron (AFDP) and a dual-pooling fusion strategy to effectively capture spatial and frequency-domain cues across modalities. Moreover, we design a Lightweight Dynamically Modulated Multi-Kernel convolution (LDMK) to perceive complex morphological structures with minimal computational overhead, replacing most convolutional operations in LIDAR. Experiments on three datasets demonstrate that our method outperforms other state-of-the-art (SOTA) methods. On the light-field depth dataset, our method achieves 0.8204 in F1 and 0.8465 in mIoU with only 5.35M parameters. Code and datasets are available at https://github.com/Karl1109/LIDAR-Mamba.

Ziming Quan, Penglei Wang, Danyang Wu, Jin Xu 0014

In recent years, multi-view graph clustering (MVGC) has attracted increasing attention from researchers. However, many existing MVGC methods focus on view-level integration through strategies like assigning weights to different views, for example, ignoring cross-view interactions between nodes. In fact, cross-view interactions at node level are crucial for extraction and fusion of semantic information. Additionally, some methods separate representation learning from clustering, which results in suboptimal clustering performance. To address these problems, we propose a novel unsupervised cross-view message passing method for MVGC. The kernel of our method is the cross-view interaction mechanism, which dynamically constructs node-specific cross-view edges based on node features and structural information. The mechanism enables adaptive interactions of informative nodes from different views, which promotes the extraction and propagation of complementary information. Besides, our method unifies representation learning and hyperspherical clustering in an end-to-end framework, which projects node representations into a hypersphere space, thereby enabling direct acquisition of balanced clustering results without dependence on external clustering methods. We provide comprehensive analyses on our method, and evaluate our method on six multi-view datasets. The results show that our method consistently achieves superior performance than existing state-of-the-art multi-view clustering methods.

Bo Wang 0108, Jin Liu 0024, Huiyuan Fu, Xin Wang 0001, Heng Zhang 0042, Huadong Ma

Exposure correction aims to restore underexposed and overexposed images to normal exposed images in a single network. However, conventional methods primarily focus on correcting non-extreme exposure cases and struggle to accurately restore lightness and structure information in extreme exposure scenarios. Through a thorough investigation, we observe that the extreme exposure correction task is limited by the lack of high-quality benchmark datasets. To address the above challenges, in this paper, we construct the first Extreme Exposure Dataset named EED by manually collecting a large number of diverse scenes. By introducing probabilistic blur kernel, EED not only ensures the rich diversity and brightness distribution of scenes but also approaches the degradation of the real world. To achieve exposure correction in extreme conditions, we propose a novel Extreme Exposure Correction Network by leveraging the mask-aware Fourier transform prior, which decouples lightness and structure components precisely. To restore severe abnormal lightness and lost structure information in extreme exposure scenes, we introduce a well-exposed referenced image to guide the coarse restoration and employ a Timestep-guided Frequency Diffusion Module for further refinement. Extensive experiments demonstrate the superiority of our dataset and method. The dataset will be available at https://github.com/juvenoia/EED.

Xiao Tan 0005, Yangyang Shen, Yan Zhang 0100, Jingwen Shao, Dian Shen, Meng Wang 0009, Beilun Wang

Dynamic Dependence Network (DDN) inference is crucial for understanding evolving relationships in multimodal time series web data, with broad applications in fields like medical and financial network analysis. The inherent dynamic nature, temporal continuity, and heterogeneous data sources in multimodal time series data pose three fundamental challenges: computational efficiency, prediction stability and robustness, and modality quality disparity. Previous methods, generally lacking utilization of multiple modalities, either struggle with computational efficiency due to the time-intensive manual hyperparameter tuning, or compromise prediction stability and robustness by neglecting temporal coherence. To address these challenges, we propose a Normalized mutual information-driven Tuning-free Dynamic Dependence Network inference method for multimodal data, namely NoTeNet. NoTeNet provides a promising paradigm that can integrate two different data modalities to enhance prediction accuracy. It uses normalized mutual information transforms noisy auxiliary data into relationship matrices and employs a kernel function for smooth temporal estimation. Additionally, NoTeNet significantly reduces the need for manual hyperparameter adjustments, offering a tuning-free approach with theoretical guarantees. On various synthetic datasets and real-world data, NoTeNet demonstrates superior prediction accuracy and efficiency without the need for hyperparameter tuning, making it potential for a wide range of web data applications.

Morgan Lindsay Heisler, Linzi Xing, Ge Shi, Hanieh Sadri, Gursimran Singh, Weiwei Zhang, Tao Ye, Ying Xiong, Yong Zhang 0004, Zhenan Fan

Huawei Cloud users leverage LoRA (Low-Rank Adaptation) as an efficient and scalable method to fine-tune and customize large language models (LLMs) for application-specific needs. However, tasks that require complex reasoning or deep contextual understanding are often hindered by biases or interference from the base model when using typical decoding methods like greedy or beam search. These biases can lead to generic or task-agnostic responses from the base model instead of leveraging the LoRA-specific adaptations. In this paper, we introduce Contrastive LoRA Decoding (CoLD), a novel decoding framework designed to maximize the use of task-specific knowledge in LoRA-adapted models, resulting in better downstream performance. CoLD utilizes contrastive decoding by scoring candidate tokens based on the divergence between the probability distributions of a LoRA-adapted expert model and the corresponding base model. This approach prioritizes tokens that better align with the LoRA's learned representations, enhancing performance for specialized tasks. Despite its effectiveness, a naive implementation of CoLD can be computationally expensive. Each decoding step requires evaluating multiple token candidates across both the base and expert models, creating significant inefficiencies. To address this challenge, we developed an optimized kernel for Huawei's Ascend NPU. CoLD demonstrates consistent performance improvements, achieving up to a 5.54% increase in task accuracy while reducing end-to-end latency by 28% compared to greedy decoding. This work offers valuable insights into practical and efficient decoding strategies for fine-tuned LLMs, particularly in resource-constrained environments, and has broad implications for applied data science in both cloud and on-premises settings.

Duc Kieu, Kien Do, Toan Nguyen 0004, Dang Nguyen 0002, Thin Nguyen

Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. This not only doubles the computational cost but also restricts their practicality. In this work, we introduce the Bidirectional Diffusion Bridge Model (BDBM), a scalable approach that facilitates bidirectional translation between two coupled distributions using a single network. BDBM leverages the Chapman-Kolmogorov Equation for bridges, enabling it to model data distribution shifts across timesteps in both forward and backward directions by exploiting the interchangeability of the initial and target timesteps within this framework. Notably, when the marginal distribution given endpoints is Gaussian, BDBM's transition kernels in both directions possess analytical forms, allowing for efficient learning with a single network. We demonstrate the connection between BDBM and existing bridge methods, such as Doob's h-transform and variational approaches, and highlight its advantages. Extensive experiments on high-resolution I2I translation tasks demonstrate that BDBM not only enables bidirectional translation with minimal additional cost but also outperforms state-of-the-art bridge models. Our source code is available at https://github.com/kvmduc/BDBM.

Yixin Ren, Haocheng Zhang, Yewei Xia, Hao Zhang 0079, Jihong Guan, Shuigeng Zhou

Score-based causal discovery methods can effectively identify causal relationships by evaluating candidate graphs and selecting the one with the highest score. One popular class of scores is kernel-based generalized score functions, which can adapt to a wide range of scenarios and work well in practice because they circumvent assumptions about causal mechanisms and data distributions. Despite these advantages, kernel-based generalized score functions pose serious computational challenges in time and space, with a time complexity of O (n3) and a memory complexity of O (n2), where n is the sample size. In this paper, we propose an approximate kernel-based generalized score function with O (n) time and space complexities by using low-rank technique and designing a set of rules to handle the complex composite matrix operations required to calculate the score, as well as developing sampling algorithms for different data types to benefit the handling of diverse data types efficiently. Our extensive causal discovery experiments on both synthetic and real-world data demonstrate that compared to the state-of-the-art method, our method can not only significantly reduce computational costs, but also achieve comparable accuracy, especially for large datasets.

Kunpeng Xu

Time series modeling is essential in finance, healthcare, and environmental science, yet nonlinear patterns, noise, and concept drift pose challenges. Although deep learning models, such as Transformer-based and recent pre-trained models, have achieved good performance across various time series tasks, they often lack interpretability, especially in co-evolving time series. This work introduces a kernel representation learning (KRL) perspective, rethinking time series modeling through kernel-induced self-representation to effectively capture temporal structures and dynamic transitions. Additionally, we establish theoretical connections between KRL and advanced deep-network models, demonstrating how kernel methods provide a principled approach to capturing complex time series behaviors.

Siyuan Yang, Cheng Song, Zhilu Lai, Wenjia Wang

Differential equations are involved in modeling many engineering problems. Many efforts have been devoted to solving differential equations. Due to the flexibility of neural networks, Physics Informed Neural Networks (PINNs) have recently been proposed to solve complex differential equations and have demonstrated superior performance in many applications. While the L2 loss function is usually a default choice in PINNs, it has been shown that the corresponding numerical solution is incorrect and unstable for some complex equations. In this work, we propose a new PINNs framework named Kernel Packet accelerated PINNs (KP-PINNs), which gives a new expression of the loss function using the reproducing kernel Hilbert space (RKHS) norm and uses the Kernel Packet (KP) method to accelerate the computation. Theoretical results show that KP-PINNs can be stable across various differential equations. Numerical experiments illustrate that KP-PINNs can solve differential equations effectively and efficiently. This framework provides a promising direction for improving the stability and accuracy of PINNs-based solvers in scientific computing.