Jihua Zhu

Qinghai Zheng, Jihua Zhu, Haoyu Tang

In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLE

Zutao Jiang, Guansong Lu, Xiaodan Liang et al.

Text-guided 3D object generation aims to generate 3D objects described by user-defined captions, which paves a flexible way to visualize what we imagined. Although some works have been devoted to solving this challenging task, these works either utilize some explicit 3D representations (e.g., mesh), which lack texture and require post-processing for rendering photo-realistic views; or require individual time-consuming optimization for every single case. Here, we make the first attempt to achieve generic text-guided cross-category 3D object generation via a new 3D-TOGO model, which integrates a text-to-views generation module and a views-to-3D generation module. The text-to-views generation module is designed to generate different views of the target 3D object given an input caption. prior-guidance, caption-guidance and view contrastive learning are proposed for achieving better view-consistency and caption similarity. Meanwhile, a pixelNeRF model is adopted for the views-to-3D generation module to obtain the implicit 3D neural representation from the previously-generated views. Our 3D-TOGO model generates 3D objects in the form of the neural radiance field with good texture and requires no time-cost optimization for every single caption. Besides, 3D-TOGO can control the category, color and shape of generated 3D objects with the input caption. Extensive experiments on the largest 3D object dataset (i.e., ABO) are conducted to verify that 3D-TOGO can better generate high-quality 3D objects according to the input captions across 98 different categories, in terms of PSNR, SSIM, LPIPS and CLIP-score, compared with text-NeRF and Dreamfields.

Junyang Wang, Yiyang Zhou, Guohai Xu et al.

Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many scenarios. Hallucination refers to the information of LVLMs' responses that does not exist in the visual input, which poses potential risks of substantial consequences. There has been limited work studying hallucination evaluation in LVLMs. In this paper, we propose Hallucination Evaluation based on Large Language Models (HaELM), an LLM-based hallucination evaluation framework. HaELM achieves an approximate 95% performance comparable to ChatGPT and has additional advantages including low cost, reproducibility, privacy preservation and local deployment. Leveraging the HaELM, we evaluate the hallucination in current LVLMs. Furthermore, we analyze the factors contributing to hallucination in LVLMs and offer helpful suggestions to mitigate the hallucination problem. Our training data and human annotation hallucination data will be made public soon.

Pengcheng Shi, Jie Zhang, Haozhe Cheng et al.

Point cloud registration is a fundamental problem in many domains. Practically, the overlap between point clouds to be registered may be relatively small. Most unsupervised methods lack effective initial evaluation of overlap, leading to suboptimal registration accuracy. To address this issue, we propose an unsupervised network Overlap Bias Matching Network (OBMNet) for partial point cloud registration. Specifically, we propose a plug-and-play Overlap Bias Matching Module (OBMM) comprising two integral components, overlap sampling module and bias prediction module. These two components are utilized to capture the distribution of overlapping regions and predict bias coefficients of point cloud common structures, respectively. Then, we integrate OBMM with the neighbor map matching module to robustly identify correspondences by precisely merging matching scores of points within the neighborhood, which addresses the ambiguities in single-point features. OBMNet can maintain efficacy even in pair-wise registration scenarios with low overlap ratios. Experimental results on extensive datasets demonstrate that our approach's performance achieves a significant improvement compared to the state-of-the-art registration approach.

Wenbiao Yan, Jihua Zhu, Yiyang Zhou et al.

Multi-view clustering can make use of multi-source information for unsupervised clustering. Most existing methods focus on learning a fused representation matrix, while ignoring the influence of private information and noise. To address this limitation, we introduce a novel Multi-view Semantic Consistency based Information Bottleneck for clustering (MSCIB). Specifically, MSCIB pursues semantic consistency to improve the learning process of information bottleneck for different views. It conducts the alignment operation of multiple views in the semantic space and jointly achieves the valuable consistent information of multi-view data. In this way, the learned semantic consistency from multi-view data can improve the information bottleneck to more exactly distinguish the consistent information and learn a unified feature representation with more discriminative consistent information for clustering. Experiments on various types of multi-view datasets show that MSCIB achieves state-of-the-art performance.

Yiyang Zhou, Qinghai Zheng, Wenbiao Yan et al.

Multi-view clustering can explore consistent information from different views to guide clustering. Most existing works focus on pursuing shallow consistency in the feature space and integrating the information of multiple views into a unified representation for clustering. These methods did not fully consider and explore the consistency in the semantic space. To address this issue, we proposed a novel Multi-level Consistency Collaborative learning framework (MCoCo) for multi-view clustering. Specifically, MCoCo jointly learns cluster assignments of multiple views in feature space and aligns semantic labels of different views in semantic space by contrastive learning. Further, we designed a multi-level consistency collaboration strategy, which utilizes the consistent information of semantic space as a self-supervised signal to collaborate with the cluster assignments in feature space. Thus, different levels of spaces collaborate with each other while achieving their own consistency goals, which makes MCoCo fully mine the consistent information of different views without fusion. Compared with state-of-the-art methods, extensive experiments demonstrate the effectiveness and superiority of our method.

Yiyang Zhou, Qinghai Zheng, Shunshun Bai et al.

In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from multiple views in an unsupervised manner. Existing UMRL methods mainly concentrate on the learning process in the feature space while ignoring the valuable semantic information hidden in different views. To address this issue, we propose a novel Semantically Consistent Multi-view Representation Learning (SCMRL), which makes efforts to excavate underlying multi-view semantic consensus information and utilize the information to guide the unified feature representation learning. Specifically, SCMRL consists of a within-view reconstruction module and a unified feature representation learning module, which are elegantly integrated by the contrastive learning strategy to simultaneously align semantic labels of both view-specific feature representations and the learned unified feature representation. In this way, the consensus information in the semantic space can be effectively exploited to constrain the learning process of unified feature representation. Compared with several state-of-the-art algorithms, extensive experiments demonstrate its superiority.

Zhuoyue Zhang, Jihua Zhu, Chaowei Fang et al.

Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth tube centers as decoder positional embeddings, causing spatio-temporal positional leakage. Moreover, they supervise inter-frame motion with deterministic proxy targets that systematically discard distributional structure by collapsing multimodal trajectory uncertainty into conditional means. To address these limitations, we propose Diffusion Masked Pretraining (DiMP), a unified self-supervised framework for dynamic point clouds. DiMP introduces diffusion modeling into both positional inference and motion learning. It first applies forward diffusion noise only to masked tube centers, then predicts clean centers from visible spatio-temporal context. This removes positional leakage while preserving visible coordinates as clean temporal anchors. DiMP also reformulates point-wise inter-frame displacement supervision as a DDPM noise-prediction objective conditioned on decoded representations. This design drives the encoder to target the full conditional distribution of plausible motions under a variational surrogate, rather than collapsing to a single deterministic estimate. Extensive experiments demonstrate that DiMP consistently improves downstream accuracy over the backbone alone, with absolute gains of 11.21% on offline action segmentation and 13.65% under causally constrained online inference.Codes are available at https://github.com/InitalZ/DiMP.git.

Zihao Guo, Jihua Zhu, Jian Liu et al.

Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning these models is computationally expensive and storage-intensive. Parameter-efficient fine-tuning (PEFT) offers a promising alternative, but existing PEFT approaches are primarily designed for Transformer-based backbones and rely on token-level prompting or feature transformation. Mamba-based backbones introduce a granularity mismatch between token-level adaptation and state-level sequence dynamics. Consequently, straightforward transfer of existing PEFT approaches to frozen Mamba backbones leads to substantial accuracy degradation and unstable optimization. To address this issue, we propose Mantis, the first Mamba-native PEFT framework for 3D PFMs. Specifically, a State-Aware Adapter (SAA) is introduced to inject lightweight task-conditioned control signals into selective state-space updates, enabling state-level adaptation while keeping the pre-trained backbone frozen. Moreover, different valid point cloud serializations are regularized by Dual-Serialization Consistency Distillation (DSCD), thereby reducing serialization-induced instability. Extensive experiments across multiple benchmarks demonstrate that our Mantis achieves competitive performance with only about 5% trainable parameters. Our code is available at https://github.com/gzhhhhhhh/Mantis.

Shiqi Li, Jihua Zhu, Yifan Xie et al.

Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based methods require ground truth labels in the supervised training process. Recognizing the handcrafted noise assumption may not be reasonable in all real-world scenarios, this paper proposes an effective rotation averaging method for mining data patterns in a learning manner while avoiding the requirement of labels. Specifically, we apply deep matrix factorization to directly solve the multiple rotation averaging problem in unconstrained linear space. For deep matrix factorization, we design a neural network model, which is explicitly low-rank and symmetric to better suit the background of multiple rotation averaging. Meanwhile, we utilize a spanning tree-based edge filtering to suppress the influence of rotation outliers. What's more, we also adopt a reweighting scheme and dynamic depth selection strategy to further improve the robustness. Our method synthesizes the merit of both optimization-based and learning-based methods. Experimental results on various datasets validate the effectiveness of our proposed method.

Yifan Xie, Jihua Zhu, Shiqi Li et al.

The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in deficiencies such as inadequate perception of global features and a lack of texture information. Actually, humans can employ visual information learned from 2D images to comprehend the 3D world. Based on this fact, we present a novel Cross-Modal Information-Guided Network (CMIGNet), which obtains global shape perception through cross-modal information to achieve precise and robust point cloud registration. Specifically, we first incorporate the projected images from the point clouds and fuse the cross-modal features using the attention mechanism. Furthermore, we employ two contrastive learning strategies, namely overlapping contrastive learning and cross-modal contrastive learning. The former focuses on features in overlapping regions, while the latter emphasizes the correspondences between 2D and 3D features. Finally, we propose a mask prediction module to identify keypoints in the point clouds. Extensive experiments on several benchmark datasets demonstrate that our network achieves superior registration performance.

Dongxu Zhang, Yingsen Wang, Yiding Sun et al.

Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance of established learning-based methods often degrades in complex, real world scenarios characterized by incomplete data, sensor noise, and low overlap regions. To address these limitations, we propose CMHANet, a novel Cross-Modal Hybrid Attention Network. Our method integrates the fusion of rich contextual information from 2D images with the geometric detail of 3D point clouds, yielding a comprehensive and resilient feature representation. Furthermore, we introduce an innovative optimization function based on contrastive learning, which enforces geometric consistency and significantly improves the model's robustness to noise and partial observations. We evaluated CMHANet on the 3DMatch and the challenging 3DLoMatch datasets. \rev{Additionally, zero-shot evaluations on the TUM RGB-D SLAM dataset verify the model's generalization capability to unseen domains.} The experimental results demonstrate that our method achieves substantial improvements in both registration accuracy and overall robustness, outperforming current techniques. We also release our code in \href{https://github.com/DongXu-Zhang/CMHANet}{https://github.com/DongXu-Zhang/CMHANet}.

Dongxu Zhang, Jihua Zhu, Shiqi Li et al.

Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling. Despite its widespread use, existing methods often fail when facing real-world challenges like heavy noise, significant occlusions, and large-scale transformations. These limitations frequently result in compromised registration accuracy and insufficient robustness in complex environments. In this paper, we propose IGASA as a novel registration framework constructed upon a Hierarchical Pyramid Architecture (HPA) designed for robust multi-scale feature extraction and fusion. The framework integrates two pivotal components consisting of the Hierarchical Cross-Layer Attention (HCLA) module and the Iterative Geometry-Aware Refinement (IGAR) module. The HCLA module utilizes skip attention mechanisms to align multi-resolution features and enhance local geometric consistency. Simultaneously, the IGAR module is designed for the fine matching phase by leveraging reliable correspondences established during coarse matching. This synergistic integration within the architecture allows IGASA to adapt effectively to diverse point cloud structures and intricate transformations. We evaluate the performance of IGASA on four widely recognized benchmark datasets including 3D(Lo)Match, KITTI, and nuScenes. Our extensive experiments consistently demonstrate that IGASA significantly surpasses state-of-the-art methods and achieves notable improvements in registration accuracy. This work provides a robust foundation for advancing point cloud registration techniques while offering valuable insights for practical 3D vision applications. The code for IGASA is available in \href{https://github.com/DongXu-Zhang/IGASA}{https://github.com/DongXu-Zhang/IGASA}.

Shiqi Li, Jihua Zhu, Yifan Xie et al.

Multiview point cloud registration plays a crucial role in robotics, automation, and computer vision fields. This paper concentrates on pose graph construction and motion synchronization within multiview registration. Previous methods for pose graph construction often pruned fully connected graphs or constructed sparse graph using global feature aggregated from local descriptors, which may not consistently yield reliable results. To identify dependable pairs for pose graph construction, we design a network model that extracts information from the matching distance between point cloud pairs. For motion synchronization, we propose another neural network model to calculate the absolute pose in a data-driven manner, rather than optimizing inaccurate handcrafted loss functions. Our model takes into account geometric distribution information and employs a modified attention mechanism to facilitate flexible and reliable feature interaction. Experimental results on diverse indoor and outdoor datasets confirm the effectiveness and generalizability of our approach. The source code is available at https://github.com/Shi-Qi-Li/MDGD.

Dongxu Zhang, Yiding Sun, Cheng Tan et al.

While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency constraints. Current efforts to mitigate this via token compression often fail by blindly applying text-centric metrics to multimodal contexts. We identify a critical failure mode termed Visual Amnesia, where linguistically redundant tokens are erroneously pruned, leading to hallucinations. To address this, we introduce V-Skip that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem. V-Skip employs a dual-path gating mechanism that weighs token importance through both linguistic surprisal and cross-modal attention flow, effectively rescuing visually salient anchors. Extensive experiments on Qwen2-VL and Llama-3.2 families demonstrate that V-Skip achieves a $2.9\times$ speedup with negligible accuracy loss. Specifically, it preserves fine-grained visual details, outperforming other baselines over 30\% on the DocVQA.

Naiwen Hu, Haozhe Cheng, Yifan Xie et al.

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal hierarchical and cross-modal semantic correlations about multi-modal data in Euclidean space. In response, we seek solutions in hyperbolic space and propose a hyperbolic image-and-pointcloud contrastive learning method (HyperIPC). For the intra-modal branch, we rely on the intrinsic geometric structure to explore the hyperbolic embedding representation of point cloud to capture invariant features. For the cross-modal branch, we leverage images to guide the point cloud in establishing strong semantic hierarchical correlations. Empirical experiments underscore the outstanding classification performance of HyperIPC. Notably, HyperIPC enhances object classification results by 2.8% and few-shot classification outcomes by 5.9% on ScanObjectNN compared to the baseline. Furthermore, ablation studies and confirmatory testing validate the rationality of HyperIPC's parameter settings and the effectiveness of its submodules.

Naiwen Hu, Haozhe Cheng, Yifan Xie et al.

Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context block and several representative target blocks. We present the context-aware decoder to enhance the reconstruction of the target blocks. Concretely, the context information is fed to the decoder continuously, facilitating the encoder in learning semantic modeling rather than memorizing the context information related to target blocks. Overall, 3D-JEPA predicts the representation of target blocks from a context block using the encoder and context-aware decoder architecture. Various downstream tasks on different datasets demonstrate 3D-JEPA's effectiveness and efficiency, achieving higher accuracy with fewer pretraining epochs, e.g., 88.65% accuracy on PB_T50_RS with 150 pretraining epochs.

Shiqi Li, Jihua Zhu, Yifan Xie

Point cloud registration plays a crucial role in various computer vision tasks, and usually demands the resolution of partial overlap registration in practice. Most existing methods perform a serial calculation of rotation and translation, while jointly predicting overlap during registration, this coupling tends to degenerate the registration performance. In this paper, we propose an effective registration method with dual branches decoupling for partial-to-partial registration, dubbed as DBDNet. Specifically, we introduce a dual branches structure to eliminate mutual interference error between rotation and translation by separately creating two individual correspondence matrices. For partial-to-partial registration, we consider overlap prediction as a preordering task before the registration procedure. Accordingly, we present an overlap predictor that benefits from explicit feature interaction, which is achieved by the powerful attention mechanism to accurately predict pointwise masks. Furthermore, we design a multi-resolution feature extraction network to capture both local and global patterns thus enhancing both overlap prediction and registration module. Experimental results on both synthetic and real datasets validate the effectiveness of our proposed method.

Yiding Sun, Jihua Zhu, Haozhe Cheng et al.

Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which hampers the scalability of self-supervised 4D models. A promising alternative is to transfer 3D pre-trained models to 4D perception tasks. However, rigorous empirical analysis reveals two critical limitations that impede transfer capability: overfitting and the modality gap. To overcome these challenges, we develop a novel "Align then Adapt" (PointATA) paradigm that decomposes parameter-efficient transfer learning into two sequential stages. Optimal-transport theory is employed to quantify the distributional discrepancy between 3D and 4D datasets, enabling our proposed point align embedder to be trained in Stage 1 to alleviate the underlying modality gap. To mitigate overfitting, an efficient point-video adapter and a spatial-context encoder are integrated into the frozen 3D backbone to enhance temporal modeling capacity in Stage 2. Notably, with the above engineering-oriented designs, PointATA enables a pre-trained 3D model without temporal knowledge to reason about dynamic video content at a smaller parameter cost compared to previous work. Extensive experiments show that PointATA can match or even outperform strong full fine-tuning models, whilst enjoying the advantage of parameter efficiency, e.g. 97.21 \% accuracy on 3D action recognition, $+8.7 \%$ on 4 D action segmentation, and 84.06\% on 4D semantic segmentation.

Shiqi Li, Jihua Zhu, Yifan Xie et al.

Multiview point cloud registration serves as a cornerstone of various computer vision tasks. Previous approaches typically adhere to a global paradigm, where a pose graph is initially constructed followed by motion synchronization to determine the absolute pose. However, this separated approach may not fully leverage the characteristics of multiview registration and might struggle with low-overlap scenarios. In this paper, we propose an incremental multiview point cloud registration method that progressively registers all scans to a growing meta-shape. To determine the incremental ordering, we employ a two-stage coarse-to-fine strategy for point cloud candidate retrieval. The first stage involves the coarse selection of scans based on neighbor fusion-enhanced global aggregation features, while the second stage further reranks candidates through geometric-based matching. Additionally, we apply a transformation averaging technique to mitigate accumulated errors during the registration process. Finally, we utilize a Reservoir sampling-based technique to address density variance issues while reducing computational load. Comprehensive experimental results across various benchmarks validate the effectiveness and generalization of our approach.

Lintong Wei, Jian Lu, Haozhe Cheng et al.

Masked autoencoders (MAE) have become a dominant paradigm in 3D representation learning, setting new performance benchmarks across various downstream tasks. Existing methods with fixed mask ratio neglect multi-level representational correlations and intrinsic geometric structures, while relying on point-wise reconstruction assumptions that conflict with the diversity of point cloud. To address these issues, we propose a 3D representation learning method, termed Point-SRA, which aligns representations through self-distillation and probabilistic modeling. Specifically, we assign different masking ratios to the MAE to capture complementary geometric and semantic information, while the MeanFlow Transformer (MFT) leverages cross-modal conditional embeddings to enable diverse probabilistic reconstruction. Our analysis further reveals that representations at different time steps in MFT also exhibit complementarity. Therefore, a Dual Self-Representation Alignment mechanism is proposed at both the MAE and MFT levels. Finally, we design a Flow-Conditioned Fine-Tuning Architecture to fully exploit the point cloud distribution learned via MeanFlow. Point-SRA outperforms Point-MAE by 5.37% on ScanObjectNN. On intracranial aneurysm segmentation, it reaches 96.07% mean IoU for arteries and 86.87% for aneurysms. For 3D object detection, Point-SRA achieves 47.3% AP@50, surpassing MaskPoint by 5.12%.

Jinqian Chen, Chang Liu, Jihua Zhu

Federated LoRA enables parameter-efficient adaptation of large language models under decentralized data and limited client resources.However, directly averaging LoRA factors is representation-dependent: the same intrinsic update admits infinitely many gauge-equivalent factorizations, so factor-level aggregation can change under arbitrary coordinate choices while the underlying update remains unchanged. This reveals a semantic mismatch in existing federated LoRA aggregation rules. We propose \textbf{GLoRA}, a gauge-aware server representation for federated LoRA.Instead of aggregating raw factors, GLoRA estimates a consensus update subspace from client projectors and aggregates client updates in shared reference coordinates, thereby representing semantic update aggregation entirely in low-rank form. To support heterogeneous client capacities, GLoRA further provides a rank-compatible readout that instantiates adapters of different ranks from the same server state without dense update reconstruction. Experiments on GLUE and SuperNI show that GLoRA consistently outperforms federated LoRA baselines under data, resource, and task heterogeneity, including heterogeneous client ranks, sparse participation, larger backbones, and unseen-task evaluation. GLoRA also achieves a favorable efficiency--performance trade-off, suggesting that effective federated LoRA requires not merely averaging low-rank factors, but defining a semantically meaningful server-side representation for aggregation.

Zhetao Hu, Yiquan Zhou, Wenyu Wang et al.

This paper presents the submission of the S4 team to the Singing Voice Conversion Challenge 2025 (SVCC2025)-a novel singing style conversion system that advances fine-grained style conversion and control within in-domain settings. To address the critical challenges of style leakage, dynamic rendering, and high-fidelity generation with limited data, we introduce three key innovations: a boundary-aware Whisper bottleneck that pools phoneme-span representations to suppress residual source style while preserving linguistic content; an explicit frame-level technique matrix, enhanced by targeted F0 processing during inference, for stable and distinct dynamic style rendering; and a perceptually motivated high-frequency band completion strategy that leverages an auxiliary standard 48kHz SVC model to augment the high-frequency spectrum, thereby overcoming data scarcity without overfitting. In the official SVCC2025 subjective evaluation, our system achieves the best naturalness performance among all submissions while maintaining competitive results in speaker similarity and technique control, despite using significantly less extra singing data than other top-performing systems. Audio samples are available online.

Xingyue Zhao, Zhongyu Li, Xiangde Luo et al.

Recent advances in deep learning have greatly facilitated the automated segmentation of ultrasound images, which is essential for nodule morphological analysis. Nevertheless, most existing methods depend on extensive and precise annotations by domain experts, which are labor-intensive and time-consuming. In this study, we suggest using simple aspect ratio annotations directly from ultrasound clinical diagnoses for automated nodule segmentation. Especially, an asymmetric learning framework is developed by extending the aspect ratio annotations with two types of pseudo labels, i.e., conservative labels and radical labels, to train two asymmetric segmentation networks simultaneously. Subsequently, a conservative-radical-balance strategy (CRBS) strategy is proposed to complementally combine radical and conservative labels. An inconsistency-aware dynamically mixed pseudo-labels supervision (IDMPS) module is introduced to address the challenges of over-segmentation and under-segmentation caused by the two types of labels. To further leverage the spatial prior knowledge provided by clinical annotations, we also present a novel loss function namely the clinical anatomy prior loss. Extensive experiments on two clinically collected ultrasound datasets (thyroid and breast) demonstrate the superior performance of our proposed method, which can achieve comparable and even better performance than fully supervised methods using ground truth annotations.

Yifan Xie, Boyu Wang, Shiqi Li et al.

As a fundamental problem in computer vision, point cloud registration aims to seek the optimal transformation for aligning a pair of point clouds. In most existing methods, the information flows are usually forward transferring, thus lacking the guidance from high-level information to low-level information. Besides, excessive high-level information may be overly redundant, and directly using it may conflict with the original low-level information. In this paper, we propose a novel Iterative Feedback Network (IFNet) for unsupervised point cloud registration, in which the representation of low-level features is efficiently enriched by rerouting subsequent high-level features. Specifically, our IFNet is built upon a series of Feedback Registration Block (FRB) modules, with each module responsible for generating the feedforward rigid transformation and feedback high-level features. These FRB modules are cascaded and recurrently unfolded over time. Further, the Feedback Transformer is designed to efficiently select relevant information from feedback high-level features, which is utilized to refine the low-level features. What's more, we incorporate a geometry-awareness descriptor to empower the network for making full use of most geometric information, which leads to more precise registration results. Extensive experiments on various benchmark datasets demonstrate the superior registration performance of our IFNet.

Xiangxiang Cui, Zhongyu Li, Xiayue Fan et al.

The intersection of medical imaging and artificial intelligence has become an important research direction in intelligent medical treatment, particularly in the analysis of medical images using deep learning for clinical diagnosis. Despite the advances, existing keyframe classification methods lack extraction of time series features, while ultrasonic video classification based on three-dimensional convolution requires uniform frame numbers across patients, resulting in poor feature extraction efficiency and model classification performance. This study proposes a novel video classification method based on CNN and LSTM, introducing NLP's long and short sentence processing scheme into video classification for the first time. The method reduces CNN-extracted image features to 1x512 dimension, followed by sorting and compressing feature vectors for LSTM training. Specifically, feature vectors are sorted by patient video frame numbers and populated with padding value 0 to form variable batches, with invalid padding values compressed before LSTM training to conserve computing resources. Experimental results demonstrate that our variable-frame CNNLSTM method outperforms other approaches across all metrics, showing improvements of 3-6% in F1 score and 1.5% in specificity compared to keyframe methods. The variable-frame CNNLSTM also achieves better accuracy and precision than equal-frame CNNLSTM. These findings validate the effectiveness of our approach in classifying variable-frame ultrasound videos and suggest potential applications in other medical imaging modalities.

Jinqian Chen, Jihua Zhu, Qinghai Zheng et al.

Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achieved in mitigating such an impact, the reliability aspect of federated models has been largely disregarded. In this study, we conduct extensive experiments to investigate the reliability of both generic and personalized federated models. Our exploration uncovers a significant finding: \textbf{federated models exhibit unreliability when faced with heterogeneous data}, demonstrating poor calibration on in-distribution test data and low uncertainty levels on out-of-distribution data. This unreliability is primarily attributed to the presence of biased projection heads, which introduce miscalibration into the federated models. Inspired by this observation, we propose the "Assembled Projection Heads" (APH) method for enhancing the reliability of federated models. By treating the existing projection head parameters as priors, APH randomly samples multiple initialized parameters of projection heads from the prior and further performs targeted fine-tuning on locally available data under varying learning rates. Such a head ensemble introduces parameter diversity into the deterministic model, eliminating the bias and producing reliable predictions via head averaging. We evaluate the effectiveness of the proposed APH method across three prominent federated benchmarks. Experimental results validate the efficacy of APH in model calibration and uncertainty estimation. Notably, APH can be seamlessly integrated into various federated approaches but only requires less than 30\% additional computation cost for 100$\times$ inferences within large models.

Jinqian Chen, Jihua Zhu, Qinghai Zheng

Federated learning encounters a critical challenge of data heterogeneity, adversely affecting the performance and convergence of the federated model. Various approaches have been proposed to address this issue, yet their effectiveness is still limited. Recent studies have revealed that the federated model suffers severe forgetting in local training, leading to global forgetting and performance degradation. Although the analysis provides valuable insights, a comprehensive understanding of the vulnerable classes and their impact factors is yet to be established. In this paper, we aim to bridge this gap by systematically analyzing the forgetting degree of each class during local training across different communication rounds. Our observations are: (1) Both missing and non-dominant classes suffer similar severe forgetting during local training, while dominant classes show improvement in performance. (2) When dynamically reducing the sample size of a dominant class, catastrophic forgetting occurs abruptly when the proportion of its samples is below a certain threshold, indicating that the local model struggles to leverage a few samples of a specific class effectively to prevent forgetting. Motivated by these findings, we propose a novel and straightforward algorithm called Federated Knowledge Anchor (FedKA). Assuming that all clients have a single shared sample for each class, the knowledge anchor is constructed before each local training stage by extracting shared samples for missing classes and randomly selecting one sample per class for non-dominant classes. The knowledge anchor is then utilized to correct the gradient of each mini-batch towards the direction of preserving the knowledge of the missing and non-dominant classes. Extensive experimental results demonstrate that our proposed FedKA achieves fast and stable convergence, significantly improving accuracy on popular benchmarks.

Jing Liu, Duanchu Wang, Haoran Gong et al.

Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem research. However, the lack of large-scale and annotated datasets has limited the widespread use of advanced intelligent techniques in this field. To address this challenge, a fully automated synthetic data generation and processing framework based on the concepts of Digital Cousins and Simulation-to-Reality (Sim2Real) is proposed, offering versatility and scalability to any size and platform. Using this process, we created the Boreal3D, the world's largest forest point cloud dataset. It includes 1000 highly realistic and structurally diverse forest plots across four different platforms, totaling 48,403 trees and over 35.3 billion points. Each point is labeled with semantic, instance, and viewpoint information, while each tree is described with structural parameters such as diameter, crown width, leaf area, and total volume. We designed and conducted extensive experiments to evaluate the potential of Boreal3D in advancing fine-grained 3D forest structure analysis in real-world applications. The results demonstrate that with certain strategies, models pre-trained on synthetic data can significantly improve performance when applied to real forest datasets. Especially, the findings reveal that fine-tuning with only 20% of real-world data enables the model to achieve performance comparable to models trained exclusively on entire real-world data, highlighting the value and potential of our proposed framework. The Boreal3D dataset, and more broadly, the synthetic data augmentation framework, is poised to become a critical resource for advancing research in large-scale 3D forest scene understanding and structural parameter estimation.

Dongxu Zhang, Ning Yang, Jihua Zhu et al.

Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet the reliability of these reasoning chains remains a critical challenge. A widely held "cascading failure" hypothesis suggests that errors are most detrimental when they occur early in the reasoning process. This paper challenges that assumption through systematic error-injection experiments, revealing a counter-intuitive phenomenon we term "Late-Stage Fragility": errors introduced in the later stages of a CoT chain are significantly more likely to corrupt the final answer than identical errors made at the beginning. To address this specific vulnerability, we introduce the Adaptive Self-Correction Chain-of-Thought (ASCoT) method. ASCoT employs a modular pipeline in which an Adaptive Verification Manager (AVM) operates first, followed by the Multi-Perspective Self-Correction Engine (MSCE). The AVM leverages a Positional Impact Score function I(k) that assigns different weights based on the position within the reasoning chains, addressing the Late-Stage Fragility issue by identifying and prioritizing high-risk, late-stage steps. Once these critical steps are identified, the MSCE applies robust, dual-path correction specifically to the failure parts. Extensive experiments on benchmarks such as GSM8K and MATH demonstrate that ASCoT achieves outstanding accuracy, outperforming strong baselines, including standard CoT. Our work underscores the importance of diagnosing specific failure modes in LLM reasoning and advocates for a shift from uniform verification strategies to adaptive, vulnerability-aware correction mechanisms.

Chongyu Wang, Kunlei Jing, Jihua Zhu et al.

Open-vocabulary semantic segmentation enables models to recognize and segment objects from arbitrary natural language descriptions, offering the flexibility to handle novel, fine-grained, or functionally defined categories beyond fixed label sets. While this capability is crucial for large-scale urban point clouds that support applications such as digital twins, smart city management, and urban analytics, it remains largely unexplored in this domain. The main obstacles are the frequent absence of high-quality, well-aligned multi-view imagery in large-scale urban point cloud datasets and the poor generalization of existing three-dimensional (3D) segmentation pipelines across diverse urban environments with substantial variation in geometry, scale, and appearance. To address these challenges, we present OpenUrban3D, the first 3D open-vocabulary semantic segmentation framework for large-scale urban scenes that operates without aligned multi-view images, pre-trained point cloud segmentation networks, or manual annotations. Our approach generates robust semantic features directly from raw point clouds through multi-view, multi-granularity rendering, mask-level vision-language feature extraction, and sample-balanced fusion, followed by distillation into a 3D backbone model. This design enables zero-shot segmentation for arbitrary text queries while capturing both semantic richness and geometric priors. Extensive experiments on large-scale urban benchmarks, including SensatUrban and SUM, show that OpenUrban3D achieves significant improvements in both segmentation accuracy and cross-scene generalization over existing methods, demonstrating its potential as a flexible and scalable solution for 3D urban scene understanding.

Chaoyi Lu, Yiding Sun, Jinqian Chen et al.

Asynchronous federated learning (AFL) accelerates training by eliminating the need to wait for stragglers, but its asynchronous nature introduces gradient staleness, where outdated gradients degrade performance. Existing solutions address this issue with gradient buffers, forming a semi-asynchronous framework. However, this approach struggles when buffers accumulate numerous stale gradients, as blindly aggregating all gradients can harm training. To address this, we propose AFBS (Asynchronous FL Buffer Selection), the first algorithm to perform gradient selection within buffers while ensuring privacy protection. Specifically, the client sends the random projection encrypted label distribution matrix before training, and the server performs client clustering based on it. During training, server scores and selects gradients within each cluster based on their informational value, discarding low-value gradients to enhance semi-asynchronous federated learning. Extensive experiments in highly heterogeneous system and data environments demonstrate AFBS's superior performance compared to state-of-the-art methods. Notably, on the most challenging task, CIFAR-100, AFBS improves accuracy by up to 4.8% over the previous best algorithm and reduces the time to reach target accuracy by 75%.

Yiting Zheng, Bohan Lin, Jinqian Chen et al.

Most current federated learning frameworks are modeled as static processes, ignoring the dynamic characteristics of the learning system. Under the limited communication budget of the central server, the flexible model architecture of a large number of clients participating in knowledge transfer requires a lower participation rate, active clients have uneven contributions, and the client scale seriously hinders the performance of FL. We consider a more general and practical federation scenario and propose a system heterogeneous federation method based on data-free knowledge distillation and two-way contrast (HFedCKD). We apply the Inverse Probability Weighted Distillation (IPWD) strategy to the data-free knowledge transfer framework. The generator completes the data features of the nonparticipating clients. IPWD implements a dynamic evaluation of the prediction contribution of each client under different data distributions. Based on the antibiased weighting of its prediction loss, the weight distribution of each client is effectively adjusted to fairly integrate the knowledge of participating clients. At the same time, the local model is split into a feature extractor and a classifier. Through differential contrast learning, the feature extractor is aligned with the global model in the feature space, while the classifier maintains personalized decision-making capabilities. HFedCKD effectively alleviates the knowledge offset caused by a low participation rate under data-free knowledge distillation and improves the performance and stability of the model. We conduct extensive experiments on image and IoT datasets to comprehensively evaluate and verify the generalization and robustness of the proposed HFedCKD framework.

Jinqian Chen, Jihua Zhu

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. Despite its widespread adoption, most FL approaches focusing solely on privacy protection fall short in scenarios where trustworthiness is crucial, necessitating advancements in secure training, dependable decision-making mechanisms, robustness on corruptions, and enhanced performance with Non-IID data. To bridge this gap, we introduce Trustworthy Personalized Federated Learning (TPFL) framework designed for classification tasks via subjective logic in this paper. Specifically, TPFL adopts a unique approach by employing subjective logic to construct federated models, providing probabilistic decisions coupled with an assessment of uncertainty rather than mere probability assignments. By incorporating a trainable heterogeneity prior to the local training phase, TPFL effectively mitigates the adverse effects of data heterogeneity. Model uncertainty and instance uncertainty are further utilized to ensure the safety and reliability of the training and inference stages. Through extensive experiments on widely recognized federated learning benchmarks, we demonstrate that TPFL not only achieves competitive performance compared with advanced methods but also exhibits resilience against prevalent malicious attacks, robustness on domain shifts, and reliability in high-stake scenarios.

Yifei Wang, Yiyang Zhou, Jihua Zhu et al.

Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are focusing on how to recover label distributions from logical labels, dubbed label enhancement (LE). Existing LE methods estimate label distributions by simply building a mapping relationship between features and label distributions under the supervision of logical labels. They typically overlook the fact that both features and logical labels are descriptions of the instance from different views. Therefore, we propose a novel method called Contrastive Label Enhancement (ConLE) which integrates features and logical labels into the unified projection space to generate high-level features by contrastive learning strategy. In this approach, features and logical labels belonging to the same sample are pulled closer, while those of different samples are projected farther away from each other in the projection space. Subsequently, we leverage the obtained high-level features to gain label distributions through a welldesigned training strategy that considers the consistency of label attributes. Extensive experiments on LDL benchmark datasets demonstrate the effectiveness and superiority of our method.

Pengcheng Shi, Haozhe Cheng, Xu Han et al.

Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent points. They cannot distinguish structural information well between different object parts, and the robustness of models is poor. To tackle these challenges, we propose an information interaction-based generative network for point cloud completion ($\mathbf{DualGenerator}$). It contains an adversarial generation path and a variational generation path, which interact with each other and share weights. DualGenerator introduces a local refinement module in generation paths, which captures general structures from partial inputs, and then refines shape details of the point cloud. It promotes completion in the unknown region and makes a distinction between different parts more obvious. Moreover, we design DGStyleGAN to improve the generation quality further. It promotes the robustness of this network combined with fusion analysis of dual-path completion results. Qualitative and quantitative evaluations demonstrate that our method is superior on MVP and Completion3D datasets. The performance will not degrade significantly after adding noise interference or sparse sampling.

Zutao Jiang, Changlin Li, Xiaojun Chang et al.

Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a pre-defined static network architecture, which inevitably leads to high computational complexity for good denoising quality. Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images. Our DDS-Net is empowered with the ability of dynamic inference by a dynamic gate, which can predictively adjust the channel configuration of networks with negligible extra computation cost. To ensure the performance of each candidate sub-network and the fairness of the dynamic gate, we propose a three-stage optimization scheme. In the first stage, we train a weight-shared slimmable super network. In the second stage, we evaluate the trained slimmable super network in an iterative way and progressively tailor the channel numbers of each layer with minimal denoising quality drop. By a single pass, we can obtain several sub-networks with good performance under different channel configurations. In the last stage, we identify easy and hard samples in an online way and train a dynamic gate to predictively select the corresponding sub-network with respect to different noisy images. Extensive experiments demonstrate our DDS-Net consistently outperforms the state-of-the-art individually trained static denoising networks.

Xinsheng Wang, Qicong Xie, Jihua Zhu et al.

Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary person as input. In contrast to previous text-driven talking head generation methods, which can only synthesize the voice of a specific person, the proposed method is capable of synthesizing speech for any person that is inaccessible in the training stage. Specifically, the proposed method decomposes the generation of synchronized speech and talking head videos into two stages, i.e., a text-to-speech (TTS) stage and a speech-driven talking head generation stage. The proposed TTS module is a face-conditioned multi-speaker TTS model that gets the speaker identity information from face images instead of speech, which allows us to synthesize a personalized voice on the basis of the input face image. To generate the talking head videos from the face images, a facial landmark-based method that can predict both lip movements and head rotations is proposed. Extensive experiments demonstrate that the proposed method is able to generate synchronized speech and talking head videos for arbitrary persons and non-persons. Synthesized speech shows consistency with the given face regarding to the synthesized voice's timbre and one's appearance in the image, and the proposed landmark-based talking head method outperforms the state-of-the-art landmark-based method on generating natural talking head videos.

Haoyu Tang, Yunxiao Wang, Jihua Zhu et al.

With the development of internet of things technologies, tremendous sensor audio data has been produced, which poses great challenges to audio-based event detection in smart cities. In this paper, we target a challenging audio-based event detection task, namely, text-to-audio grounding. In addition to precisely localizing all of the desired on- and off-sets in the untrimmed audio, this challenging new task requires extensive acoustic and linguistic comprehension as well as the reasoning for the crossmodal matching relations between the audio and query. The current approaches often treat the query as an entire one through a global query representation in order to address those issues. We contend that this strategy has several drawbacks. Firstly, the interactions between the query and the audio are not fully utilized. Secondly, it has not distinguished the importance of different keywords in a query. In addition, since the audio clips are of arbitrary lengths, there exist many segments which are irrelevant to the query but have not been filtered out in the approach. This further hinders the effective grounding of desired segments. Motivated by the above concerns, a novel Cross-modal Graph Interaction (CGI) model is proposed to comprehensively model the relations between the words in a query through a novel language graph. To capture the fine-grained relevances between the audio and query, a cross-modal attention module is introduced to generate snippet-specific query representations and automatically assign higher weights to keywords with more important semantics. Furthermore, we develop a cross-gating module for the audio and query to weaken irrelevant parts and emphasize the important ones.

Jihua Zhu, Di Wang, Jiaxi Mu et al.

The normal distributions transform (NDT) is an effective paradigm for the point set registration. This method is originally designed for pair-wise registration and it will suffer from great challenges when applied to multi-view registration. Under the NDT framework, this paper proposes a novel multi-view registration method, named 3D multi-view registration based on the normal distributions transform (3DMNDT), which integrates the K-means clustering and Lie algebra solver to achieve multi-view registration. More specifically, the multi-view registration is cast into the problem of maximum likelihood estimation. Then, the K-means algorithm is utilized to divide all data points into different clusters, where a normal distribution is computed to locally models the probability of measuring a data point in each cluster. Subsequently, the registration problem is formulated by the NDT-based likelihood function. To maximize this likelihood function, the Lie algebra solver is developed to sequentially optimize each rigid transformation. The proposed method alternately implements data point clustering, NDT computing, and likelihood maximization until desired registration results are obtained. Experimental results tested on benchmark data sets illustrate that the proposed method can achieve state-of-the-art performance for multi-view registration.

Yanlin Ma, Jihua Zhu, Zhongyu Li et al.

Recently, Expectation-maximization (EM) algorithm has been introduced as an effective means to solve multi-view registration problem. Most of the previous methods assume that each data point is drawn from the Gaussian Mixture Model (GMM), which is difficult to deal with the noise with heavy-tail or outliers. Accordingly, this paper proposed an effective registration method based on Student's t Mixture Model (StMM). More specially, we assume that each data point is drawn from one unique StMM, where its nearest neighbors (NNs) in other point sets are regarded as the t-distribution centroids with equal covariances, membership probabilities, and fixed degrees of freedom. Based on this assumption, the multi-view registration problem is formulated into the maximization of the likelihood function including all rigid transformations. Subsequently, the EM algorithm is utilized to optimize rigid transformations as well as the only t-distribution covariance for multi-view registration. Since only a few model parameters require to be optimized, the proposed method is more likely to obtain the desired registration results. Besides, all t-distribution centroids can be obtained by the NN search method, it is very efficient to achieve multi-view registration. What's more, the t-distribution takes the noise with heavy-tail into consideration, which makes the proposed method be inherently robust to noises and outliers. Experimental results tested on benchmark data sets illustrate its superior performance on robustness and accuracy over state-of-the-art methods.

Xinsheng Wang, Siyuan Feng, Jihua Zhu et al.

This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as input and predicts the spectrogram of speech that describes this image. The final speech audio is obtained from the predicted spectrogram via WaveNet. Extensive experiments on the public benchmark database Flickr8k demonstrate that the proposed SAS is able to synthesize natural spoken descriptions for images, indicating that synthesizing spoken descriptions for images while bypassing text and phonemes is feasible.

Qinghai Zheng, Jihua Zhu, Yuanyuan Ma et al.

This study investigates the problem of multi-view subspace clustering, the goal of which is to explore the underlying grouping structure of data collected from different fields or measurements. Since data do not always comply with the linear subspace models in many real-world applications, most existing multi-view subspace clustering methods that based on the shallow linear subspace models may fail in practice. Furthermore, underlying graph information of multi-view data is always ignored in most existing multi-view subspace clustering methods. To address aforementioned limitations, we proposed the novel multi-view subspace clustering networks with local and global graph information, termed MSCNLG, in this paper. Specifically, autoencoder networks are employed on multiple views to achieve latent smooth representations that are suitable for the linear assumption. Simultaneously, by integrating fused multi-view graph information into self-expressive layers, the proposed MSCNLG obtains the common shared multi-view subspace representation, which can be used to get clustering results by employing the standard spectral clustering algorithm. As an end-to-end trainable framework, the proposed method fully investigates the valuable information of multiple views. Comprehensive experiments on six benchmark datasets validate the effectiveness and superiority of the proposed MSCNLG.

Qinghai Zheng, Yu Zhang, Jihua Zhu et al.

As a hot research topic, many multi-view clustering approaches are proposed over the past few years. Nevertheless, most existing algorithms merely take the consensus information among different views into consideration for clustering. Actually, it may hinder the multi-view clustering performance in real-life applications, since different views usually contain diverse statistic properties. To address this problem, we propose a novel Tensor-based Intrinsic Subspace Representation Learning (TISRL) for multi-view clustering in this paper. Concretely, the rank preserving decomposition is proposed firstly to effectively deal with the diverse statistic information contained in different views. Then, to achieve the intrinsic subspace representation, the tensor-singular value decomposition based low-rank tensor constraint is also utilized in our method. It can be seen that specific information contained in different views is fully investigated by the rank preserving decomposition, and the high-order correlations of multi-view data are also mined by the low-rank tensor constraint. The objective function can be optimized by an augmented Lagrangian multiplier based alternating direction minimization algorithm. Experimental results on nine common used real-world multi-view datasets illustrate the superiority of TISRL.

Qinghai Zheng, Jihua Zhu, Shuangxun Ma

This paper focuses on the multi-view clustering, which aims to promote clustering results with multi-view data. Usually, most existing works suffer from the issues of parameter selection and high computational complexity. To overcome these limitations, we propose a Multi-view Hierarchical Clustering (MHC), which partitions multi-view data recursively at multiple levels of granularity. Specifically, MHC consists of two important components: the cosine distance integration (CDI) and the nearest neighbor agglomeration (NNA). The CDI can explore the underlying complementary information of multi-view data so as to learn an essential distance matrix, which is utilized in NNA to obtain the clustering results. Significantly, the proposed MHC can be easily and effectively employed in real-world applications without parameter selection. Experiments on nine benchmark datasets illustrate the superiority of our method comparing to several state-of-the-art multi-view clustering methods.

Haoyu Tang, Jihua Zhu, Meng Liu et al.

Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap between textual query and video contents. To tackle those problems, early approaches adopt the sliding window or uniform sampling to collect video clips first and then match each clip with the query. Obviously, these strategies are time-consuming and often lead to unsatisfied accuracy in localization due to the unpredictable length of the golden moment. To avoid the limitations, researchers recently attempt to directly predict the relevant moment boundaries without the requirement to generate video clips first. One mainstream approach is to generate a multimodal feature vector for the target query and video frames (e.g., concatenation) and then use a regression approach upon the multimodal feature vector for boundary detection. Although some progress has been achieved by this approach, we argue that those methods have not well captured the cross-modal interactions between the query and video frames. In this paper, we propose an Attentive Cross-modal Relevance Matching (ACRM) model which predicts the temporal boundaries based on an interaction modeling. In addition, an attention module is introduced to assign higher weights to query words with richer semantic cues, which are considered to be more important for finding relevant video contents. Another contribution is that we propose an additional predictor to utilize the internal frames in the model training to improve the localization accuracy. Extensive experiments on two datasets TACoS and Charades-STA demonstrate the superiority of our method over several state-of-the-art methods. Ablation studies have been also conducted to examine the effectiveness of different modules in our ACRM model.

Dou Xu, Chang Cai, Chaowei Fang et al.

Annotating histopathological images is a time-consuming andlabor-intensive process, which requires broad-certificated pathologistscarefully examining large-scale whole-slide images from cells to tissues.Recent frontiers of transfer learning techniques have been widely investi-gated for image understanding tasks with limited annotations. However,when applied for the analytics of histology images, few of them can effec-tively avoid the performance degradation caused by the domain discrep-ancy between the source training dataset and the target dataset, suchas different tissues, staining appearances, and imaging devices. To thisend, we present a novel method for the unsupervised domain adaptationin histopathological image analysis, based on a backbone for embeddinginput images into a feature space, and a graph neural layer for propa-gating the supervision signals of images with labels. The graph model isset up by connecting every image with its close neighbors in the embed-ded feature space. Then graph neural network is employed to synthesizenew feature representation from every image. During the training stage,target samples with confident inferences are dynamically allocated withpseudo labels. The cross-entropy loss function is used to constrain thepredictions of source samples with manually marked labels and targetsamples with pseudo labels. Furthermore, the maximum mean diversityis adopted to facilitate the extraction of domain-invariant feature repre-sentations, and contrastive learning is exploited to enhance the categorydiscrimination of learned features. In experiments of the unsupervised do-main adaptation for histopathological image classification, our methodachieves state-of-the-art performance on four public datasets

Xinyuan Liu, Jihua Zhu, Qinghai Zheng et al.

Label distribution learning (LDL) is an interpretable and general learning paradigm that has been applied in many real-world applications. In contrast to the simple logical vector in single-label learning (SLL) and multi-label learning (MLL), LDL assigns labels with a description degree to each instance. In practice, two challenges exist in LDL, namely, how to address the dimensional gap problem during the learning process of LDL and how to exactly recover label distributions from existing logical labels, i.e., Label Enhancement (LE). For most existing LDL and LE algorithms, the fact that the dimension of the input matrix is much higher than that of the output one is alway ignored and it typically leads to the dimensional reduction owing to the unidirectional projection. The valuable information hidden in the feature space is lost during the mapping process. To this end, this study considers bidirectional projections function which can be applied in LE and LDL problems simultaneously. More specifically, this novel loss function not only considers the mapping errors generated from the projection of the input space into the output one but also accounts for the reconstruction errors generated from the projection of the output space back to the input one. This loss function aims to potentially reconstruct the input data from the output data. Therefore, it is expected to obtain more accurate results. Finally, experiments on several real-world datasets are carried out to demonstrate the superiority of the proposed method for both LE and LDL.

Xinsheng Wang, Tingting Qiao, Jihua Zhu et al.

An estimated half of the world's languages do not have a written form, making it impossible for these languages to benefit from any existing text-based technologies. In this paper, a speech-to-image generation (S2IG) framework is proposed which translates speech descriptions to photo-realistic images without using any text information, thus allowing unwritten languages to potentially benefit from this technology. The proposed S2IG framework, named S2IGAN, consists of a speech embedding network (SEN) and a relation-supervised densely-stacked generative model (RDG). SEN learns the speech embedding with the supervision of the corresponding visual information. Conditioned on the speech embedding produced by SEN, the proposed RDG synthesizes images that are semantically consistent with the corresponding speech descriptions. Extensive experiments on two public benchmark datasets CUB and Oxford-102 demonstrate the effectiveness of the proposed S2IGAN on synthesizing high-quality and semantically-consistent images from the speech signal, yielding a good performance and a solid baseline for the S2IG task.

Jihua Zhu, Jie Hu, Huimin Lu et al.

Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set of relative motions, where the original method is sensitive to outliers due to using the Frobenius norm error in the optimization. Accordingly, this paper proposes a novel robust motion averaging method based on the maximum correntropy criterion (MCC). Specifically, the correntropy measure is used instead of utilizing Frobenius norm error to improve the robustness of motion averaging against outliers. According to the half-quadratic technique, the correntropy measure based optimization problem can be solved by the alternating minimization procedure, which includes operations of weight assignment and weighted motion averaging. Further, we design a selection strategy of adaptive kernel width to take advantage of correntropy. Experimental results on benchmark data sets illustrate that the new method has superior performance on accuracy and robustness for multi-view registration.