arXiv subjects

Fei Ma

Publications and source records attributed to Fei Ma.

At least 91 records · Page 5Linked to original sources

arXiv2025

MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach

Face editing modifies the appearance of face, which plays a key role in customization and enhancement of personal images. Although much work have achieved remarkable success in text-driven face editing, they still face significant challenges as none of them simultaneously fulfill the characteristics of diversity, controllability and flexibility. To address this challenge, we propose MuseFace, a text-driven face editing framework, which relies solely on text prompt to enable face editing. Specifically, MuseFace integrates a Text-to-Mask diffusion model and a semantic-aware face editing model, capable of directly generating fine-grained semantic masks from text and performing face editing. The Text-to-Mask diffusion model provides \textit{diversity} and \textit{flexibility} to the framework, while the semantic-aware face editing model ensures \textit{controllability} of the framework. Our framework can create fine-grained semantic masks, making precise face editing possible, and significantly enhancing the controllability and flexibility of face editing models. Extensive experiments demonstrate that MuseFace achieves superior high-fidelity performance.

cs.CV↗

arXiv2025

Object Isolated Attention for Consistent Story Visualization

Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline. One of the main difficulties is maintaining character consistency while creating natural and contextually fitting scenes--an area where many existing methods struggle. In this paper, we propose an enhanced Transformer module that uses separate self attention and cross attention mechanisms, leveraging prior knowledge from pre-trained diffusion models to ensure logical scene creation. The isolated self attention mechanism improves character consistency by refining attention maps to reduce focus on irrelevant areas and highlight key features of the same character. Meanwhile, the isolated cross attention mechanism independently processes each character's features, avoiding feature fusion and further strengthening consistency. Notably, our method is training-free, allowing the continuous generation of new characters and storylines without re-tuning. Both qualitative and quantitative evaluations show that our approach outperforms current methods, demonstrating its effectiveness.

cs.CV↗

arXiv2025

Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba

Event cameras draw inspiration from biological systems, boasting low latency and high dynamic range while consuming minimal power. The most current approach to processing Event Cloud often involves converting it into frame-based representations, which neglects the sparsity of events, loses fine-grained temporal information, and increases the computational burden. In contrast, Point Cloud is a popular representation for processing 3-dimensional data and serves as an alternative method to exploit local and global spatial features. Nevertheless, previous point-based methods show an unsatisfactory performance compared to the frame-based method in dealing with spatio-temporal event streams. In order to bridge the gap, we propose EventMamba, an efficient and effective framework based on Point Cloud representation by rethinking the distinction between Event Cloud and Point Cloud, emphasizing vital temporal information. The Event Cloud is subsequently fed into a hierarchical structure with staged modules to process both implicit and explicit temporal features. Specifically, we redesign the global extractor to enhance explicit temporal extraction among a long sequence of events with temporal aggregation and State Space Model (SSM) based Mamba. Our model consumes minimal computational resources in the experiments and still exhibits SOTA point-based performance on six different scales of action recognition datasets. It even outperformed all frame-based methods on both Camera Pose Relocalization (CPR) and eye-tracking regression tasks. Our code is available at: https://github.com/rhwxmx/EventMamba.

cs.CV↗

arXiv2025

Topological Structures of Sets and their Subsets

For real application and theoretical investigation of ordinary hypergraphs and non-ordinary hypergraphs, researchers need to establish standard rules and feasible operating methods. We propose a visualization tool for investigating hypergraphs by means of the natural topological structure of finite sets and their subsets, so we are able to construct various non-ordinary hypergraphs, and to reveal topological properties (such as hamiltonian cycles, maximal planar graphs), colorings, connectivity, hypergraph group, isomorphism and homomorphism of hypergraphs.

math.HO↗

arXiv2025

UniSync: A Unified Framework for Audio-Visual Synchronization

Precise audio-visual synchronization in speech videos is crucial for content quality and viewer comprehension. Existing methods have made significant strides in addressing this challenge through rule-based approaches and end-to-end learning techniques. However, these methods often rely on limited audio-visual representations and suboptimal learning strategies, potentially constraining their effectiveness in more complex scenarios. To address these limitations, we present UniSync, a novel approach for evaluating audio-visual synchronization using embedding similarities. UniSync offers broad compatibility with various audio representations (e.g., Mel spectrograms, HuBERT) and visual representations (e.g., RGB images, face parsing maps, facial landmarks, 3DMM), effectively handling their significant dimensional differences. We enhance the contrastive learning framework with a margin-based loss component and cross-speaker unsynchronized pairs, improving discriminative capabilities. UniSync outperforms existing methods on standard datasets and demonstrates versatility across diverse audio-visual representations. Its integration into talking face generation frameworks enhances synchronization quality in both natural and AI-generated content.

cs.CV↗

arXiv2025

Image Fusion for Cross-Domain Sequential Recommendation

Cross-Domain Sequential Recommendation (CDSR) aims to predict future user interactions based on historical interactions across multiple domains. The key challenge in CDSR is effectively capturing cross-domain user preferences by fully leveraging both intra-sequence and inter-sequence item interactions. In this paper, we propose a novel method, Image Fusion for Cross-Domain Sequential Recommendation (IFCDSR), which incorporates item image information to better capture visual preferences. Our approach integrates a frozen CLIP model to generate image embeddings, enriching original item embeddings with visual data from both intra-sequence and inter-sequence interactions. Additionally, we employ a multiple attention layer to capture cross-domain interests, enabling joint learning of single-domain and cross-domain user preferences. To validate the effectiveness of IFCDSR, we re-partitioned four e-commerce datasets and conducted extensive experiments. Results demonstrate that IFCDSR significantly outperforms existing methods.

cs.IR↗

arXiv2025

Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions

Embodied multimodal large models (EMLMs) have gained significant attention in recent years due to their potential to bridge the gap between perception, cognition, and action in complex, real-world environments. This comprehensive review explores the development of such models, including Large Language Models (LLMs), Large Vision Models (LVMs), and other models, while also examining other emerging architectures. We discuss the evolution of EMLMs, with a focus on embodied perception, navigation, interaction, and simulation. Furthermore, the review provides a detailed analysis of the datasets used for training and evaluating these models, highlighting the importance of diverse, high-quality data for effective learning. The paper also identifies key challenges faced by EMLMs, including issues of scalability, generalization, and real-time decision-making. Finally, we outline future directions, emphasizing the integration of multimodal sensing, reasoning, and action to advance the development of increasingly autonomous systems. By providing an in-depth analysis of state-of-the-art methods and identifying critical gaps, this paper aims to inspire future advancements in EMLMs and their applications across diverse domains.

cs.RO↗

arXiv2025

Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction

Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these approaches struggle to efficiently model a human-interactive object with n movable parts, requiring 2^n separate models to represent all discrete states. To overcome this limitation, we propose Inter3D, a new benchmark and approach for novel state synthesis of human-interactive objects. We introduce a self-collected dataset featuring commonly encountered interactive objects and a new evaluation pipeline, where only individual part states are observed during training, while part combination states remain unseen. We also propose a strong baseline approach that leverages Space Discrepancy Tensors to efficiently modelling all states of an object. To alleviate the impractical constraints on camera trajectories across training states, we propose a Mutual State Regularization mechanism to enhance the spatial density consistency of movable parts. In addition, we explore two occupancy grid sampling strategies to facilitate training efficiency. We conduct extensive experiments on the proposed benchmark, showcasing the challenges of the task and the superiority of our approach.

cs.GR↗

arXiv2025

PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting

Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies. This paper presents a novel transformer architecture for time series forecasting, incorporating two key innovations: parameter sharing (PS) and Spatial-Temporal Segment Attention (SegAtt). We also define the time series segment as the concatenation of sequence patches from the same positions across different variables. The proposed model, PSformer, reduces the number of training parameters through the parameter sharing mechanism, thereby improving model efficiency and scalability. The introduction of SegAtt could enhance the capability of capturing local spatio-temporal dependencies by computing attention over the segments, and improve global representation by integrating information across segments. The combination of parameter sharing and SegAtt significantly improves the forecasting performance. Extensive experiments on benchmark datasets demonstrate that PSformer outperforms popular baselines and other transformer-based approaches in terms of accuracy and scalability, establishing itself as an accurate and scalable tool for time series forecasting.

cs.LG↗

arXiv2025

Non-Hermitian Dirac cones with valley-dependent lifetimes

Relativistic quasiparticles emerging from band degeneracies in crystals play crucial roles in the transport and topological properties of materials and metamaterials. Quasiparticles are commonly described by Hermitian Hamiltonians, with non-Hermiticity usually considered detrimental. In this work, we show that such an assumption of Hermiticity can be lifted to bring quasiparticles into non-Hermitian regime. We propose a concrete lattice model containing two Dirac cones with valley-dependent lifetimes. The lifetime contrast enables an ultra-strong valley selection rule: only one valley can survive in the long-time limit regardless of the excitation, lattice shape and other details. This property leads to an effective parity anomaly with a single Dirac cone and offers a simple way to generate vortex states. Additionally, extending non-Hermitian features to boundaries generates valley kink states with valley-locked lifetimes, making them effectively unidirectional and more resistant against inter-valley scattering. All these phenomena are experimentally demonstrated in a non-Hermitian electric circuit lattice.

cond-mat.mes-hall↗

arXiv2025

CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis

Colonoscopy is crucial for identifying adenomatous polyps and preventing colorectal cancer. However, developing robust models for polyp detection is challenging by the limited size and accessibility of existing colonoscopy datasets. While previous efforts have attempted to synthesize colonoscopy images, current methods suffer from instability and insufficient data diversity. Moreover, these approaches lack precise control over the generation process, resulting in images that fail to meet clinical quality standards. To address these challenges, we propose CCIS-DIFF, a Controlled generative model for high-quality Colonoscopy Image Synthesis based on a Diffusion architecture. Our method offers precise control over both the spatial attributes (polyp location and shape) and clinical characteristics of polyps that align with clinical descriptions. Specifically, we introduce a blur mask weighting strategy to seamlessly blend synthesized polyps with the colonic mucosa, and a text-aware attention mechanism to guide the generated images to reflect clinical characteristics. Notably, to achieve this, we construct a new multi-modal colonoscopy dataset that integrates images, mask annotations, and corresponding clinical text descriptions. Experimental results demonstrate that our method generates high-quality, diverse colonoscopy images with fine control over both spatial constraints and clinical consistency, offering valuable support for downstream segmentation and diagnostic tasks.

cs.CV↗

arXiv2024

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV.

cs.CV↗

arXiv2024

PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis

Talking head synthesis with arbitrary speech audio is a crucial challenge in the field of digital humans. Recently, methods based on radiance fields have received increasing attention due to their ability to synthesize high-fidelity and identity-consistent talking heads from just a few minutes of training video. However, due to the limited scale of the training data, these methods often exhibit poor performance in audio-lip synchronization and visual quality. In this paper, we propose a novel 3D Gaussian-based method called PointTalk, which constructs a static 3D Gaussian field of the head and deforms it in sync with the audio. It also incorporates an audio-driven dynamic lip point cloud as a critical component of the conditional information, thereby facilitating the effective synthesis of talking heads. Specifically, the initial step involves generating the corresponding lip point cloud from the audio signal and capturing its topological structure. The design of the dynamic difference encoder aims to capture the subtle nuances inherent in dynamic lip movements more effectively. Furthermore, we integrate the audio-point enhancement module, which not only ensures the synchronization of the audio signal with the corresponding lip point cloud within the feature space, but also facilitates a deeper understanding of the interrelations among cross-modal conditional features. Extensive experiments demonstrate that our method achieves superior high-fidelity and audio-lip synchronization in talking head synthesis compared to previous methods.

cs.SD↗

arXiv2024

A Review of Human Emotion Synthesis Based on Generative Technology

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interactions. Recent advancements in generative models, such as Autoencoders, Generative Adversarial Networks, Diffusion Models, Large Language Models, and Sequence-to-Sequence Models, have significantly contributed to the development of this field. However, there is a notable lack of comprehensive reviews in this field. To address this problem, this paper aims to address this gap by providing a thorough and systematic overview of recent advancements in human emotion synthesis based on generative models. Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used. Then, the review covers the application of different generative models to emotion synthesis based on a variety of modalities, including facial images, speech, and text. It also examines mainstream evaluation metrics. Additionally, the review presents some major findings and suggests future research directions, providing a comprehensive understanding of the role of generative technology in the nuanced domain of emotion synthesis.

cs.LG↗

arXiv2024

Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation

Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method.

cs.CV↗

arXiv2024

Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness. The typical framework involves using image-level labels as training data to generate pixel-level pseudo-labels with refinements. Recently, methods based on Vision Transformers (ViT) have demonstrated superior capabilities in generating reliable pseudo-labels, particularly in recognizing complete object regions, compared to CNN methods. However, current ViT-based approaches have some limitations in the use of patch embeddings, being prone to being dominated by certain abnormal patches, as well as many multi-stage methods being time-consuming and lengthy in training, thus lacking efficiency. Therefore, in this paper, we introduce a novel ViT-based WSSS method named \textit{Adaptive Patch Contrast} (APC) that significantly enhances patch embedding learning for improved segmentation effectiveness. APC utilizes an Adaptive-K Pooling (AKP) layer to address the limitations of previous max pooling selection methods. Additionally, we propose a Patch Contrastive Learning (PCL) to enhance patch embeddings, thereby further improving the final results. Furthermore, we improve upon the existing multi-stage training framework without CAM by transforming it into an end-to-end single-stage training approach, thereby enhancing training efficiency. The experimental results show that our approach is effective and efficient, outperforming other state-of-the-art WSSS methods on the PASCAL VOC 2012 and MS COCO 2014 dataset within a shorter training duration.

cs.CV↗

arXiv2024

Design and Experimental Application of a Radon Diffusion Chamber for Determining Diffusion Coefficients in Membrane Materials

In recent years, the issue of radon emanation and diffusion has become a critical concern for rare decay experiments, such as JUNO and PandaX-4T. This paper introduces a detector design featuring a symmetric radon detector cavity for the quantitative assessment of membrane materials' radon blocking capabilities. The performance of this design is evaluated through the application of Fick's Law and the diffusion equation considering material solubility. Our detector has completed measurements of radon diffusion coefficients for four types of membrane materials currently used in experiments, which also confirms the rationality of this detector design. The findings are instrumental in guiding the selection and evaluation of optimal materials for radon shielding to reduce radon background, contributing to boost sensitivities of rare event research.

physics.ins-det↗

arXiv2024

Cloud Adversarial Example Generation for Remote Sensing Image Classification

Most existing adversarial attack methods for remote sensing images merely add adversarial perturbations or patches, resulting in unnatural modifications. Clouds are common atmospheric effects in remote sensing images. Generating clouds on these images can produce adversarial examples better aligning with human perception. In this paper, we propose a Perlin noise based cloud generation attack method. Common Perlin noise based cloud generation is a random, non-optimizable process, which cannot be directly used to attack the target models. We design a Perlin Gradient Generator Network (PGGN), which takes a gradient parameter vector as input and outputs the grids of Perlin noise gradient vectors at different scales. After a series of computations based on the gradient vectors, cloud masks at corresponding scales can be produced. These cloud masks are then weighted and summed depending on a mixing coefficient vector and a scaling factor to produce the final cloud masks. The gradient vector, coefficient vector and scaling factor are collectively represented as a cloud parameter vector, transforming the cloud generation into a black-box optimization problem. The Differential Evolution (DE) algorithm is employed to solve for the optimal solution of the cloud parameter vector, achieving a query-based black-box attack. Detailed experiments confirm that this method has strong attack capabilities and achieves high query efficiency. Additionally, we analyze the transferability of the generated adversarial examples and their robustness in adversarial defense scenarios.

cs.CV↗