Hui Tian

Wanli Ni, Jingheng Zheng, Hui Tian

Implementing existing federated learning in massive Internet of Things (IoT) networks faces critical challenges such as imbalanced and statistically heterogeneous data and device diversity. To this end, we propose a semi-federated learning (SemiFL) framework to provide a potential solution for the realization of intelligent IoT. By seamlessly integrating the centralized and federated paradigms, our SemiFL framework shows high scalability in terms of the number of IoT devices even in the presence of computing-limited sensors. Furthermore, compared to traditional learning approaches, the proposed SemiFL can make better use of distributed data and computing resources, due to the collaborative model training between the edge server and local devices. Simulation results show the effectiveness of our SemiFL framework for massive IoT networks. The code can be found at https://github.com/niwanli/SemiFL_IoT.

Hui Tian, Chenyang Zhu, Yifei Shi et al.

Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient training and a novel regularization for robustness to sparse sampling. The core idea of SuperUDF draws inspiration from the classical surface approximation operator of locally optimal projection (LOP). The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF. Based on that, a number of inductive biases on UDF geometry and a pre-learned geometry prior are devised to learn UDF estimation efficiently. A novel regularization loss is proposed to make SuperUDF robust to sparse sampling. Furthermore, we also contribute a learning-based mesh extraction from the estimated UDFs. Extensive evaluations demonstrate that SuperUDF outperforms the state of the arts on several public datasets in terms of both quality and efficiency. Code url is https://github.com/THHHomas/SuperUDF.

Hui Tian, Zheng Qin, Renjiao Yi et al.

Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays. Classic solutions, such as Poisson surface reconstruction, require point normals as extra input to perform reasonable results. Modern transformer-based methods can work without normals, while the results are less fine-grained due to limited encoding performance in local fusion from discrete points. We introduce a novel normalized matrix attention transformer (Tensorformer) to perform high-quality reconstruction. The proposed matrix attention allows for simultaneous point-wise and channel-wise message passing, while the previous vector attention loses neighbor point information across different channels. It brings more degree of freedom in feature learning and thus facilitates better modeling of local geometries. Our method achieves state-of-the-art on two commonly used datasets, ShapeNetCore and ABC, and attains 4% improvements on IOU on ShapeNet. Code can be accessed https://github.com/THHHomas/Tensorformer6.

Jingheng Zheng, Hui Tian, Wanli Ni et al.

Over-the-air federated learning (AirFL) allows devices to train a learning model in parallel and synchronize their local models using over-the-air computation. The integrity of AirFL is vulnerable due to the obscurity of the local models aggregated over-the-air. This paper presents a novel framework to balance the accuracy and integrity of AirFL, where multi-antenna devices and base station (BS) are jointly optimized with a reconfigurable intelligent surface (RIS). The key contributions include a new and non-trivial problem jointly considering the model accuracy and integrity of AirFL, and a new framework that transforms the problem into tractable subproblems. Under perfect channel state information (CSI), the new framework minimizes the aggregated model's distortion and retains the local models' recoverability by optimizing the transmit beamformers of the devices, the receive beamformers of the BS, and the RIS configuration in an alternating manner. Under imperfect CSI, the new framework delivers a robust design of the beamformers and RIS configuration to combat non-negligible channel estimation errors. As corroborated experimentally, the novel framework can achieve comparable accuracy to the ideal FL while preserving local model recoverability under perfect CSI, and improve the accuracy when the number of receive antennas is small or moderate under imperfect CSI.

Jingheng Zheng, Wanli Ni, Hui Tian et al.

Under the organization of the base station (BS), wireless federated learning (FL) enables collaborative model training among multiple devices. However, the BS is merely responsible for aggregating local updates during the training process, which incurs a waste of the computational resource at the BS. To tackle this issue, we propose a semi-federated learning (SemiFL) paradigm to leverage the computing capabilities of both the BS and devices for a hybrid implementation of centralized learning (CL) and FL. Specifically, each device sends both local gradients and data samples to the BS for training a shared global model. To improve communication efficiency over the same time-frequency resources, we integrate over-the-air computation for aggregation and non-orthogonal multiple access for transmission by designing a novel transceiver structure. To gain deep insights, we conduct convergence analysis by deriving a closed-form optimality gap for SemiFL and extend the result to two extra cases. In the first case, the BS uses all accumulated data samples to calculate the CL gradient, while a decreasing learning rate is adopted in the second case. Our analytical results capture the destructive effect of wireless communication and show that both FL and CL are special cases of SemiFL. Then, we formulate a non-convex problem to reduce the optimality gap by jointly optimizing the transmit power and receive beamformers. Accordingly, we propose a two-stage algorithm to solve this intractable problem, in which we provide the closed-form solutions to the beamformers. Extensive simulation results on two real-world datasets corroborate our theoretical analysis, and show that the proposed SemiFL outperforms conventional FL and achieves 3.2% accuracy gain on the MNIST dataset compared to state-of-the-art benchmarks.

Jianyang Ren, Wanli Ni, Hui Tian

In this letter, we study a wireless federated learning (FL) system where network pruning is applied to local users with limited resources. Although pruning is beneficial to reduce FL latency, it also deteriorates learning performance due to the information loss. Thus, a trade-off problem between communication and learning is raised. To address this challenge, we quantify the effects of network pruning and packet error on the learning performance by deriving the convergence rate of FL with a non-convex loss function. Then, closed-form solutions for pruning control and bandwidth allocation are proposed to minimize the weighted sum of FL latency and FL performance. Finally, numerical results demonstrate that 1) our proposed solution can outperform benchmarks in terms of cost reduction and accuracy guarantee, and 2) a higher pruning rate would bring less communication overhead but also worsen FL accuracy, which is consistent with our theoretical analysis.

Xiurong Jiang, Lin Zhu, Yifan Hou et al.

RGB-thermal salient object detection (RGB-T SOD) aims to locate the common prominent objects of an aligned visible and thermal infrared image pair and accurately segment all the pixels belonging to those objects. It is promising in challenging scenes such as nighttime and complex backgrounds due to the insensitivity to lighting conditions of thermal images. Thus, the key problem of RGB-T SOD is to make the features from the two modalities complement and adjust each other flexibly, since it is inevitable that any modalities of RGB-T image pairs failure due to challenging scenes such as extreme light conditions and thermal crossover. In this paper, we propose a novel mirror complementary Transformer network (MCNet) for RGB-T SOD. Specifically, we introduce a Transformer-based feature extraction module to effective extract hierarchical features of RGB and thermal images. Then, through the attention-based feature interaction and serial multiscale dilated convolution (SDC) based feature fusion modules, the proposed model achieves the complementary interaction of low-level features and the semantic fusion of deep features. Finally, based on the mirror complementary structure, the salient regions of the two modalities can be accurately extracted even one modality is invalid. To demonstrate the robustness of the proposed model under challenging scenes in real world, we build a novel RGB-T SOD dataset VT723 based on a large public semantic segmentation RGB-T dataset used in the autonomous driving domain. Expensive experiments on benchmark and VT723 datasets show that the proposed method outperforms state-of-the-art approaches, including CNN-based and Transformer-based methods. The code and dataset will be released later at https://github.com/jxr326/SwinMCNet.

Weizhi Liu, Yue Li, Dongdong Lin et al.

Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this challenge. Yet, this defensive measure unintentionally fuels the continued refinement of generative models. Watermarking emerges as a proactive and sustainable tactic, preemptively regulating the creation and dissemination of synthesized content. Thus, this paper, as a pioneer, proposes the generative robust audio watermarking method (Groot), presenting a paradigm for proactively supervising the synthesized audio and its source diffusion models. In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously, facilitated by parameter-fixed diffusion models equipped with a dedicated encoder. The watermark embedded within the audio can subsequently be retrieved by a lightweight decoder. The experimental results highlight Groot's outstanding performance, particularly in terms of robustness, surpassing that of the leading state-of-the-art methods. Beyond its impressive resilience against individual post-processing attacks, Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%.

Kaibo Huang, Jin Tan, Yukun Wei et al.

LLM-based agents are increasingly deployed to autonomously solve complex tasks, raising urgent needs for IP protection and regulatory provenance. While content watermarking effectively attributes LLM-generated outputs, it fails to directly identify the high-level planning behaviors (e.g., tool and subgoal choices) that govern multi-step execution. Critically, watermarking at the planning-behavior layer faces unique challenges: minor distributional deviations in decision-making can compound during long-term agent operation, degrading utility, and many agents operate as black boxes that are difficult to intervene in directly. To bridge this gap, we propose AgentMark, a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. It operates by eliciting an explicit behavior distribution from the agent and applying distribution-preserving conditional sampling, enabling deployment under black-box APIs while remaining compatible with action-layer content watermarking. Experiments across embodied, tool-use, and social environments demonstrate practical multi-bit capacity, robust recovery from partial logs, and utility preservation. The code is available at https://github.com/Tooooa/AgentMark.

Judy X Yang, Jun Zhou, Jing Wang et al.

Classifying hyperspectral images is a difficult task in remote sensing, due to their complex high-dimensional data. To address this challenge, we propose HSIMamba, a novel framework that uses bidirectional reversed convolutional neural network pathways to extract spectral features more efficiently. Additionally, it incorporates a specialized block for spatial analysis. Our approach combines the operational efficiency of CNNs with the dynamic feature extraction capability of attention mechanisms found in Transformers. However, it avoids the associated high computational demands. HSIMamba is designed to process data bidirectionally, significantly enhancing the extraction of spectral features and integrating them with spatial information for comprehensive analysis. This approach improves classification accuracy beyond current benchmarks and addresses computational inefficiencies encountered with advanced models like Transformers. HSIMamba were tested against three widely recognized datasets Houston 2013, Indian Pines, and Pavia University and demonstrated exceptional performance, surpassing existing state-of-the-art models in HSI classification. This method highlights the methodological innovation of HSIMamba and its practical implications, which are particularly valuable in contexts where computational resources are limited. HSIMamba redefines the standards of efficiency and accuracy in HSI classification, thereby enhancing the capabilities of remote sensing applications. Hyperspectral imaging has become a crucial tool for environmental surveillance, agriculture, and other critical areas that require detailed analysis of the Earth surface. Please see our code in HSIMamba for more details.

Xiang Gao, Hui Tian, Yanming Zhu et al.

Decoding visual information from electroencephalography (EEG) signals remains a fundamental challenge in brain-computer interfaces and medical rehabilitation. Existing EEG visual decoding methods mainly focus on learning a single global EEG embedding for cross-modal alignment, but they largely overlook the staged and hierarchical characteristics of human visual processing. To address this limitation, we propose a neuroscience-inspired staged representation learning framework that reformulates EEG visual decoding as a stage-specific representation decomposition problem. The proposed framework organizes EEG representation learning into three complementary phases: low-level visual representation learning, high-level semantic representation learning, and integrative information fusion. To strengthen semantic modeling, we further introduce a multimodal dual-level semantic learning mechanism that separates coarse label-level semantics from fine image-level visual-semantic information. In addition, semantic latent channels are introduced as computational representation channels generated from observed visual EEG signals, expanding the channel-level semantic representation space for structured semantic abstraction and cross-modal alignment. Extensive experiments on the THINGS-EEG benchmark demonstrate that the proposed method achieves superior performance under subject-dependent zero-shot evaluation and improved exact retrieval under subject-independent zero-shot evaluation. Additional analyses, including layer-wise retrieval, temporal accumulation, expanded multi-image retrieval, and ablation studies, further support the effectiveness of staged decomposition and structured semantic modeling. These results suggest that explicitly modeling staged perceptual, semantic, and integrative representations provides an effective neuroscience-inspired framework for EEG-based visual decoding.

Yue Li, Linying Xue, Kaiqing Lin et al.

Recent advances in GAN and diffusion models have significantly improved the realism and controllability of facial deepfake manipulation, raising serious concerns regarding privacy, security, and identity misuse. Proactive defenses attempt to counter this threat by injecting adversarial perturbations into images before manipulation takes place. However, existing approaches remain limited in effectiveness due to suboptimal perturbation injection strategies and are typically designed under white-box assumptions, targeting only simple GAN-based attribute editing. These constraints hinder their applicability in practical real-world scenarios. In this paper, we propose AEGIS, the first diffusion-guided paradigm in which the AdvErsarial facial images are Generated for Identity Shielding. We observe that the limited defense capability of existing approaches stems from the peak-clipping constraint, where perturbations are forcibly truncated due to a fixed $L_\infty$-bounded. To overcome this limitation, instead of directly modifying pixels, AEGIS injects adversarial perturbations into the latent space along the DDIM denoising trajectory, thereby decoupling the perturbation magnitude from pixel-level constraints and allowing perturbations to adaptively amplify where most effective. The extensible design of AEGIS allows the defense to be expanded from purely white-box use to also support black-box scenarios through a gradient-estimation strategy. Extensive experiments across GAN and diffusion-based deepfake generators show that AEGIS consistently delivers strong defense effectiveness while maintaining high perceptual quality. In white-box settings, it achieves robust manipulation disruption, whereas in black-box settings, it demonstrates strong cross-model transferability.

Judy X Yang, Jun Zhou, Jing Wang et al.

The fusion of hyperspectral and LiDAR data has been an active research topic. Existing fusion methods have ignored the high-dimensionality and redundancy challenges in hyperspectral images, despite that band selection methods have been intensively studied for hyperspectral image (HSI) processing. This paper addresses this significant gap by introducing a cross-attention mechanism from the transformer architecture for the selection of HSI bands guided by LiDAR data. LiDAR provides high-resolution vertical structural information, which can be useful in distinguishing different types of land cover that may have similar spectral signatures but different structural profiles. In our approach, the LiDAR data are used as the "query" to search and identify the "key" from the HSI to choose the most pertinent bands for LiDAR. This method ensures that the selected HSI bands drastically reduce redundancy and computational requirements while working optimally with the LiDAR data. Extensive experiments have been undertaken on three paired HSI and LiDAR data sets: Houston 2013, Trento and MUUFL. The results highlight the superiority of the cross-attention mechanism, underlining the enhanced classification accuracy of the identified HSI bands when fused with the LiDAR features. The results also show that the use of fewer bands combined with LiDAR surpasses the performance of state-of-the-art fusion models.

Hui Tian, Kai Xu

Point cloud reconstruction from raw point cloud has been an important topic in computer graphics for decades, especially due to its high demand in modeling and rendering applications. An important way to solve this problem is establishing a local geometry to fit the local curve. However, previous methods build either a local plane or polynomial curve. Local plane brings the loss of sharp feature and the boundary artefacts on open surface. Polynomial curve is hard to combine with neural network due to the local coordinate consistent problem. To address this, we propose a novel polyhedral surface to represent local surface. This method provides more flexible to represent sharp feature and surface boundary on open surface. It does not require any local coordinate system, which is important when introducing neural networks. Specifically, we use normals to construct the polyhedral surface, including both dihedral and trihedral surfaces using 2 and 3 normals, respectively. Our method achieves state-of-the-art results on three commonly used datasets (ShapeNetCore, ABC, and ScanNet). Code will be released upon acceptance.

Xin Wang, Hong Shen, Hui Tian et al.

Coflow has emerged as a fundamental application-layer abstraction in distributed systems, representing communication dependencies and enabling collaborative management of related flows to enhance job completion efficiency. To meet the increasing bandwidth demands of modern data center networks (DCNs), optical circuit switches are widely deployed due to their high capacity and energy efficiency. Simultaneously, DCN deployments are evolving towards heterogeneous parallel architectures, where multiple independent optical circuit switching (OCS) cores operate concurrently to facilitate bandwidth expansion and incremental upgrades. However, existing research on coflow scheduling in multi-core switching fabrics primarily focuses on electrical packet switching (EPS) networks, with a few known results on OCS networks without or with a poor performance guarantee. This paper studies the coflow scheduling problem in multi-core OCS networks under the not-all-stop (i.e., asynchronous) reconfiguration model, focusing on two major challenges of overcoming cross-core coupling for inter-core traffic allocation and satisfying the constraints of port exclusivity and reconfiguration overhead for intra-core circuit scheduling. To minimize total weighted coflow completion time (CCT), we propose an efficient algorithm by integrating linear programming-guided (LP-guided) global coflow ordering, inter-core flow allocation and intra-core circuit scheduling that achieves approximation ratios of 8K and 8K+1 for zero and arbitrary release times of coflows, respectively, where K is the number of OCS cores. This framework is also applicable to H-core EPS networks, providing approximation guarantees of 4H and 4H+1 for zero-time and arbitrary-time release, respectively.

Wanli Ni, Haofeng Sun, Huiqing Ao et al.

Large artificial intelligence (AI) models exhibit remarkable capabilities in various application scenarios, but deploying them at the network edge poses significant challenges due to issues such as data privacy, computational resources, and latency. In this paper, we explore federated fine-tuning and collaborative reasoning techniques to facilitate the implementation of large AI models in resource-constrained wireless networks. Firstly, promising applications of large AI models within specific domains are discussed. Subsequently, federated fine-tuning methods are proposed to adapt large AI models to specific tasks or environments at the network edge, effectively addressing the challenges associated with communication overhead and enhancing communication efficiency. These methodologies follow clustered, hierarchical, and asynchronous paradigms to effectively tackle privacy issues and eliminate data silos. Furthermore, to enhance operational efficiency and reduce latency, efficient frameworks for model collaborative reasoning are developed, which include decentralized horizontal collaboration, cloud-edge-end vertical collaboration, and multi-access collaboration. Next, simulation results demonstrate the effectiveness of our proposed methods in reducing the fine-tuning loss of large AI models across various downstream tasks. Finally, several open challenges and research opportunities are outlined.

Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew et al.

With the rapid advancement of artificial intelligence and deep learning, medical image analysis has become a critical tool in modern healthcare, significantly improving diagnostic accuracy and efficiency. However, AI-based methods also raise serious privacy concerns, as medical images often contain highly sensitive patient information. This review offers a comprehensive overview of privacy-preserving techniques in medical image analysis, including encryption, differential privacy, homomorphic encryption, federated learning, and generative adversarial networks. We explore the application of these techniques across various medical image analysis tasks, such as diagnosis, pathology, and telemedicine. Notably, we organizes the review based on specific challenges and their corresponding solutions in different medical image analysis applications, so that technical applications are directly aligned with practical issues, addressing gaps in the current research landscape. Additionally, we discuss emerging trends, such as zero-knowledge proofs and secure multi-party computation, offering insights for future research. This review serves as a valuable resource for researchers and practitioners and can help advance privacy-preserving in medical image analysis.

Xin Wang, Hong Shen, Hui Tian et al.

Coflow provides a key application-layer abstraction for capturing communication patterns, enabling the efficient coordination of parallel data flows to reduce job completion times in distributed systems. Modern data center networks (DCNs) are employing multiple independent optical circuit switching (OCS) cores operating concurrently to meet the massive bandwidth demands of application jobs. However, existing coflow scheduling research primarily focuses on the single-core setting, with multi-core fabrics only for EPS (electrical packet switching) networks. To address this gap, this paper studies the coflow scheduling problem in multi-core OCS networks under the not-all-stop reconfiguration model in which one circuit's reconfiguration does not interrupt other circuits. The challenges stem from two aspects: (i) cross-core coupling induced by traffic assignment across heterogeneous cores; and (ii) per-core OCS scheduling constraints, namely port exclusivity and reconfiguration delay. We propose an approximation algorithm that jointly integrates cross-core flow assignment and per-core circuit scheduling to minimize the total weighted coflow completion time (CCT) and establish a provable worst-case performance guarantee. Furthermore, our algorithm framework can be directly applied to the multi-core EPS scenario with the corresponding approximation ratio under packet-switched fabrics. Trace-driven simulations using real Facebook workloads demonstrate that our algorithm effectively reduces weighted CCT and tail CCT.

Ziqiao Peng, Wentao Hu, Junyuan Ma et al.

Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses. The absence of these synchronizations is a fundamental flaw, leading to unrealistic results. To address the critical issue of synchronization, identified as the ''devil'' in creating realistic talking heads, we introduce SyncTalk++, which features a Dynamic Portrait Renderer with Gaussian Splatting to ensure consistent subject identity preservation and a Face-Sync Controller that aligns lip movements with speech while innovatively using a 3D facial blendshape model to reconstruct accurate facial expressions. To ensure natural head movements, we propose a Head-Sync Stabilizer, which optimizes head poses for greater stability. Additionally, SyncTalk++ enhances robustness to out-of-distribution (OOD) audio by incorporating an Expression Generator and a Torso Restorer, which generate speech-matched facial expressions and seamless torso regions. Our approach maintains consistency and continuity in visual details across frames and significantly improves rendering speed and quality, achieving up to 101 frames per second. Extensive experiments and user studies demonstrate that SyncTalk++ outperforms state-of-the-art methods in synchronization and realism. We recommend watching the supplementary video: https://ziqiaopeng.github.io/synctalk++.

Hui Tian, Kai Xu

Surface reconstruction from point clouds is a crucial task in the fields of computer vision and computer graphics. SDF-based methods excel at reconstructing smooth meshes with minimal error and artefacts but struggle with representing open surfaces. On the other hand, UDF-based methods can effectively represent open surfaces but often introduce noise, leading to artefacts in the mesh. In this work, we propose a novel approach that directly predicts the intersection points between line segment of point pairs and implicit surfaces. To achieve it, we propose two modules named Relative Intersection Module and Sign Module respectively with the feature of point pair as input. To preserve the continuity of the surface, we also integrate symmetry into the two modules, which means the position of predicted intersection will not change even if the input order of the point pair changes. This method not only preserves the ability to represent open surfaces but also eliminates most artefacts on the mesh. Our approach demonstrates state-of-the-art performance on three datasets: ShapeNet, MGN, and ScanNet. The code will be made available upon acceptance.

Wanli Ni, Hui Tian, Shuai Wang et al.

Federated split learning (FedSL) has emerged as a promising paradigm for enabling collaborative intelligence in industrial Internet of Things (IoT) systems, particularly in smart factories where data privacy, communication efficiency, and device heterogeneity are critical concerns. In this article, we present a comprehensive study of FedSL frameworks tailored for resource-constrained robots in industrial scenarios. We compare synchronous, asynchronous, hierarchical, and heterogeneous FedSL frameworks in terms of workflow, scalability, adaptability, and limitations under dynamic industrial conditions. Furthermore, we systematically categorize token fusion strategies into three paradigms: input-level (pre-fusion), intermediate-level (intra-fusion), and output-level (post-fusion), and summarize their respective strengths in industrial applications. We also provide adaptive optimization techniques to enhance the efficiency and feasibility of FedSL implementation, including model compression, split layer selection, computing frequency allocation, and wireless resource management. Simulation results validate the performance of these frameworks under industrial detection scenarios. Finally, we outline open issues and research directions of FedSL in future smart manufacturing systems.

Wentao Hu, Shunkai Li, Ziqiao Peng et al.

Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head rotations and out-of-distribution (OOD) audio. Moreover, they are constrained by the need for time-consuming, identity-specific training. We believe the core issue lies in the lack of sufficient 3D priors, which limits the extrapolation capabilities of synthesized talking heads. To address this, we propose GGTalker, which synthesizes talking heads through a combination of generalizable priors and identity-specific adaptation. We introduce a two-stage Prior-Adaptation training strategy to learn Gaussian head priors and adapt to individual characteristics. We train Audio-Expression and Expression-Visual priors to capture the universal patterns of lip movements and the general distribution of head textures. During the Customized Adaptation, individual speaking styles and texture details are precisely modeled. Additionally, we introduce a color MLP to generate fine-grained, motion-aligned textures and a Body Inpainter to blend rendered results with the background, producing indistinguishable, photorealistic video frames. Comprehensive experiments show that GGTalker achieves state-of-the-art performance in rendering quality, 3D consistency, lip-sync accuracy, and training efficiency.

Yue Li, Weizhi Liu, Dongdong Lin et al.

The rapid advancement of generative models has led to the synthesis of real-fake ambiguous voices. To erase the ambiguity, embedding watermarks into the frequency-domain features of synthesized voices has become a common routine. However, the robustness achieved by choosing the frequency domain often comes at the expense of fine-grained voice features, leading to a loss of fidelity. Maximizing the comprehensive learning of time-domain features to enhance fidelity while maintaining robustness, we pioneer a \textbf{\underline{t}}emporal-aware \textbf{\underline{r}}ob\textbf{\underline{u}}st wat\textbf{\underline{e}}rmarking (\emph{True}) method for protecting the speech and singing voice. For this purpose, the integrated content-driven encoder is designed for watermarked waveform reconstruction, which is structurally lightweight. Additionally, the temporal-aware gated convolutional network is meticulously designed to bit-wise recover the watermark. Comprehensive experiments and comparisons with existing state-of-the-art methods have demonstrated the superior fidelity and vigorous robustness of the proposed \textit{True} achieving an average PESQ score of 4.63.

Judy X Yang, Jun Zhou, Jing Wang et al.

Band selection in hyperspectral imaging (HSI) is critical for optimising data processing and enhancing analytical accuracy. Traditional approaches have predominantly concentrated on analysing spectral and pixel characteristics within individual bands independently. These approaches overlook the potential benefits of integrating multiple data sources, such as Light Detection and Ranging (LiDAR), and is further challenged by the limited availability of labeled data in HSI processing, which represents a significant obstacle. To address these challenges, this paper introduces a novel unsupervised band selection framework that incorporates attention mechanisms and an Autoencoder for reconstruction-based band selection. Our methodology distinctively integrates HSI with LiDAR data through an attention score, using a convolutional Autoencoder to process the combined feature mask. This fusion effectively captures essential spatial and spectral features and reduces redundancy in hyperspectral datasets. A comprehensive comparative analysis of our innovative fused band selection approach is performed against existing unsupervised band selection and fusion models. We used data sets such as Houston 2013, Trento, and MUUFLE for our experiments. The results demonstrate that our method achieves superior classification accuracy and significantly outperforms existing models. This enhancement in HSI band selection, facilitated by the incorporation of LiDAR features, underscores the considerable advantages of integrating features from different sources.

Wentao Hu, Xiurong Jiang, Jiarun Liu et al.

In the field of few-shot learning (FSL), extensive research has focused on improving network structures and training strategies. However, the role of data processing modules has not been fully explored. Therefore, in this paper, we propose Meta-DM, a generalized data processing module for FSL problems based on diffusion models. Meta-DM is a simple yet effective module that can be easily integrated with existing FSL methods, leading to significant performance improvements in both supervised and unsupervised settings. We provide a theoretical analysis of Meta-DM and evaluate its performance on several algorithms. Our experiments show that combining Meta-DM with certain methods achieves state-of-the-art results.

Chenfei Shi, Yan Xue, Chuan Jiang et al.

Endoscopic diagnosis is an important means for gastric polyp detection. In this paper, a panoramic image of gastroscopy is developed, which can display the inner surface of the stomach intuitively and comprehensively. Moreover, the proposed automatic detection solution can help doctors locate the polyps automatically, and reduce missed diagnosis. The main contributions of this paper are: firstly, a gastroscopic panorama reconstruction method is developed. The reconstruction does not require additional hardware devices, and can solve the problem of texture dislocation and illumination imbalance properly; secondly, an end-to-end multi-object detection for gastroscopic panorama is trained based on deep learning framework. Compared with traditional solutions, the automatic polyp detection system can locate all polyps in the inner wall of stomach in real time and assist doctors to find the lesions. Thirdly, the system was evaluated in the Affiliated Hospital of Zhejiang University. The results show that the average error of the panorama is less than 2 mm, the accuracy of the polyp detection is 95%, and the recall rate is 99%. In addition, the research roadmap of this paper has guiding significance for endoscopy-assisted detection of other human soft cavities.

Zhipeng Wu, Hui Tian, Xuzhen Zhu et al.

Matrix factorization (MF) is extensively used to mine the user preference from explicit ratings in recommender systems. However, the reliability of explicit ratings is not always consistent, because many factors may affect the user's final evaluation on an item, including commercial advertising and a friend's recommendation. Therefore, mining the reliable ratings of user is critical to further improve the performance of the recommender system. In this work, we analyze the deviation degree of each rating in overall rating distribution of user and item, and propose the notion of user-based rating centrality and item-based rating centrality, respectively. Moreover, based on the rating centrality, we measure the reliability of each user rating and provide an optimized matrix factorization recommendation algorithm. Experimental results on two popular recommendation datasets reveal that our method gets better performance compared with other matrix factorization recommendation algorithms, especially on sparse datasets.

Weilin Cong, Sanyuan Zhao, Hui Tian et al.

Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and alignment methods have been proposed. Recent studies have utilized the relation between face detection and alignment to make models computationally efficiency, however they ignore the connection between each cascade CNNs. In this paper, we propose an structure to propose higher quality training data for End-to-End cascade network training, which give computers more space to automatic adjust weight parameter and accelerate convergence. Experiments demonstrate considerable improvement over existing detection and alignment models.

Xuzhen Zhu, Hui Tian, Zheng Hu et al.

The explosive growth of information challenges people's capability in finding out items fitting to their own interests. Recommender systems provide an efficient solution by automatically push possibly relevant items to users according to their past preferences. Recommendation algorithms usually embody the causality from what having been collected to what should be recommended. In this article, we argue that in many cases, a user's interests are stable, and thus the previous and future preferences are highly consistent. The temporal order of collections then does not necessarily imply a causality relationship. We further propose a consistence-based algorithm that outperforms the state-of-the-art recommendation algorithms in disparate real data sets, including \textit{Netflix}, \textit{MovieLens}, \textit{Amazon} and \textit{Rate Your Music}.

Xuzhen Zhu, Hui Tian, Shimin Cai

Personalized recommendation attracts a surge of interdisciplinary researches. Especially, similarity based methods in applications of real recommendation systems achieve great success. However, the computations of similarities are overestimated or underestimated outstandingly due to the defective strategy of unidirectional similarity estimation. In this paper, we solve this drawback by leveraging mutual correction of forward and backward similarity estimations, and propose a new personalized recommendation index, i.e., corrected similarity based inference (CSI). Through extensive experiments on four benchmark datasets, the results show a greater improvement of CSI in comparison with these mainstream baselines. And the detailed analysis is presented to unveil and understand the origin of such difference between CSI and mainstream indices.

Xuzhen Zhu, Hui Tian, Haifeng Liu et al.

The problem of personalized recommendation in an ocean of data attracts more and more attention recently. Most traditional researches ignore the popularity of the recommended object, which resulting in low personality and accuracy. In this Letter, we proposed a personalized recommendation method based on weighted object network, punishing the recommended object that is the crowd's popular selection, namely, Anti-popularity index(AP), which can give enhanced personality, accuracy and diversity in contrast to mainstream baselines with a low computational complexity.