Query：
学者姓名：郑清海
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Zero-shot Natural Language Video Localization (NLVL) aims to automatically generate moments and corresponding pseudo queries from raw videos for the training of the localization model without any manual annotations. Existing approaches typically produce pseudo queries as simple words, which overlook the complexity of queries in real-world scenarios. Considering the powerful text modeling capabilities of large language models (LLMs), leveraging LLMs to generate complete queries that are closer to human descriptions is a potential solution. However, directly integrating LLMs into existing approaches introduces several issues, including insensitivity, isolation, and lack of regulation, which prevent the full exploitation of LLMs to enhance zero-shot NLVL performance. To address these issues, we propose BTDP, an innovative framework for Boundary-aware Temporal Dynamic Pseudo-supervision pairs generation. Our method contains two crucial operations: 1) Boundary Segmentation that identifies both visual boundaries and semantic boundaries to generate the atomic segments and activity descriptions, tackling the issue of insensitivity. 2) Context Aggregation that employs the LLMs with a self-evaluation process to aggregate and summarize global video information for optimized pseudo moment-query pairs, tackling the issue of isolation and lack of regulation. Comprehensive experimental results on the Charades-STA and ActivityNet Captions datasets demonstrate the effectiveness of our BTDP method. © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Semantic Segmentation Semantic Segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Deng, Xiongwen , Tang, Haoyu , Jiang, Han et al. Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization [C] . 2025 : 2717-2725 . |
| MLA | Deng, Xiongwen et al. "Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization" . (2025) : 2717-2725 . |
| APA | Deng, Xiongwen , Tang, Haoyu , Jiang, Han , Zheng, Qinghai , Zhu, Jihua . Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization . (2025) : 2717-2725 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Zero-shot Natural Language Video Localization (NLVL) aims to automatically generate moments and corresponding pseudo queries from raw videos for the training of the localization model without any manual annotations. Existing approaches typically produce pseudo queries as simple words, which overlook the complexity of queries in real-world scenarios. Considering the powerful text modeling capabilities of large language models (LLMs), leveraging LLMs to generate complete queries that are closer to human descriptions is a potential solution. However, directly integrating LLMs into existing approaches introduces several issues, including insensitivity, isolation, and lack of regulation, which prevent the full exploitation of LLMs to enhance zero-shot NLVL performance. To address these issues, we propose BTDP, an innovative framework for Boundary-aware Temporal Dynamic Pseudo-supervision pairs generation. Our method contains two crucial operations: 1) Boundary Segmentation that identifies both visual boundaries and semantic boundaries to generate the atomic segments and activity descriptions, tackling the issue of insensitivity. 2) Context Aggregation that employs the LLMs with a self-evaluation process to aggregate and summarize global video information for optimized pseudo moment-query pairs, tackling the issue of isolation and lack of regulation. Comprehensive experimental results on the Charades-STA and ActivityNet Captions datasets demonstrate the effectiveness of our BTDP method.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Deng, Xiongwen , Tang, Haoyu , Jiang, Han et al. Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization [J]. | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 , 2025 : 2717-2725 . |
| MLA | Deng, Xiongwen et al. "Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization" . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 (2025) : 2717-2725 . |
| APA | Deng, Xiongwen , Tang, Haoyu , Jiang, Han , Zheng, Qinghai , Zhu, Jihua . Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 , 2025 , 2717-2725 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Driven by the complementarity and consistency inherent in multiview data, multiview clustering (MVC) has garnered widespread attention in various domains. Real-world data often encounters the issue of missing information, leading to a surge of interest in the domain of incomplete MVC (IMVC). Despite existing approaches having made significant progress in addressing IMVC, two significant challenges persist: 1) many alignment-based methodologies tend to overlook the topological relationships among instances and 2) the view representations based on completion lack reconstructive properties, casting doubt on their alignment with the actual view representations. In response, we present a novel approach termed neighbor-based completion for addressing IMVC (NBIMVC), which capitalizes on the topological information among instances and the consistent information across views. Specifically, our method uses autoencoders to learn feature representations for each view and leverages nearest-neighbor relationships between unique and complete instances to complete missing features in missing views. Subsequently, we enforce hard negative alignment constraints on complete paired instances in the feature space. Finally, we ensure the consistency of views in the semantic space by employing cluster information and a shared clustering network, which facilitates the final multiview categories output and effectively resolves the IMVC problem. Extensive experimental evaluations validate the efficacy of our proposed method, showcasing comparable or superior performance to existing approaches.
Keyword ：
Autoencoders Autoencoders Contrastive clustering Contrastive clustering Contrastive learning Contrastive learning Deep learning Deep learning incomplete multiview clustering (IMVC) incomplete multiview clustering (IMVC) Learning systems Learning systems multiview clustering (MVC) multiview clustering (MVC) Mutual information Mutual information Pattern classification Pattern classification Representation learning Representation learning Semantics Semantics Space exploration Space exploration Training Training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yan, Wenbiao , Zhu, Jihua , Zhou, Yiyang et al. Neighbor-Based Completion for Addressing Incomplete Multiview Clustering [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2025 , 36 (8) : 15374-15384 . |
| MLA | Yan, Wenbiao et al. "Neighbor-Based Completion for Addressing Incomplete Multiview Clustering" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 36 . 8 (2025) : 15374-15384 . |
| APA | Yan, Wenbiao , Zhu, Jihua , Zhou, Yiyang , Chen, Jinqian , Cheng, Haozhe , Yue, Kun et al. Neighbor-Based Completion for Addressing Incomplete Multiview Clustering . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2025 , 36 (8) , 15374-15384 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view clustering has attracted significant attention in recent years because it can leverage the consistent and complementary information of multiple views to improve clustering performance. However, effectively fuse the information and balance the consistent and complementary information of multiple views are common challenges faced by multi-view clustering. Most existing multi-view fusion works focus on weighted-sum fusion and concatenating fusion, which unable to fully fuse the underlying information, and not consider balancing the consistent and complementary information of multiple views. To this end, we propose Cross-view Fusion for Multi-view Clustering (CFMVC). Specifically, CFMVC combines deep neural network and graph convolutional network for cross-view information fusion, which fully fuses feature information and structural information of multiple views. In order to balance the consistent and complementary information of multiple views, CFMVC enhances the correlation among the same samples to maximize the consistent information while simultaneously reinforcing the independence among different samples to maximize the complementary information. Experimental results on several multi-view datasets demonstrate the effectiveness of CFMVC for multi-view clustering task.
Keyword ：
Cross-view Cross-view deep neural network deep neural network graph convolutional network graph convolutional network multi-view clustering multi-view clustering multi-view fusion multi-view fusion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huang, Zhijie , Huang, Binqiang , Zheng, Qinghai et al. Cross-View Fusion for Multi-View Clustering [J]. | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 : 621-625 . |
| MLA | Huang, Zhijie et al. "Cross-View Fusion for Multi-View Clustering" . | IEEE SIGNAL PROCESSING LETTERS 32 (2025) : 621-625 . |
| APA | Huang, Zhijie , Huang, Binqiang , Zheng, Qinghai , Yu, Yuanlong . Cross-View Fusion for Multi-View Clustering . | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 , 621-625 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view clustering learns consistent information from multi-view data, aiming to achieve more significant clustering characteristics. However, data in real-world scenarios often exhibit temporal or spatial asynchrony, leading to views with unaligned instances. Existing methods primarily address this issue by learning transformation matrices to align unaligned instances, but this process of learning differentiable transformation matrices is cumbersome. To address the challenge of partially unaligned instances, we propose P artially M ulti-view C lustering via R e-alignment (PMVCR). Our approach integrates representation learning and data alignment through a two-stage training and a re-alignment process. Specifically, our training process consists of three stages: (i) In the coarse-grained alignment stage, we construct negative instance pairs for unaligned instances and utilize contrastive learning to preliminarily learn the view representations of the instances. (ii) In there- alignment stage, we match unaligned instances based on the similarity of their view representations, aligning them with the primary view. (iii) In the fine-grained alignment stage, we further enhance the discriminative power of the view representations and the model's ability to differentiate between clusters. Compared to existing models, our method effectively leverages information between unaligned samples and enhances model generalization by constructing negative instance pairs. Clustering experiments on several popular multi-view datasets demonstrate the effectiveness and superiority of our method. Our code is publicly available at https://github.com/WenB777/PMVCR.git.
Keyword ：
Contrastive learning Contrastive learning Multi-view clustering Multi-view clustering Partial view-aligned multi-view learning Partial view-aligned multi-view learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yan, Wenbiao , Zhu, Jihua , Chen, Jinqian et al. Partially multi-view clustering via re-alignment [J]. | NEURAL NETWORKS , 2025 , 182 . |
| MLA | Yan, Wenbiao et al. "Partially multi-view clustering via re-alignment" . | NEURAL NETWORKS 182 (2025) . |
| APA | Yan, Wenbiao , Zhu, Jihua , Chen, Jinqian , Cheng, Haozhe , Bai, Shunshun , Duan, Liang et al. Partially multi-view clustering via re-alignment . | NEURAL NETWORKS , 2025 , 182 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
As a widely used method in signal processing, Principal Component Analysis (PCA) performs both the compression and the recovery of high dimensional data by leveraging the linear transformations. Considering the robustness of PCA, how to discriminate correct samples and outliers in PCA is a crucial and challenging issue. In this paper, we present a general model, which conducts PCA via a non-decreasing concave regularized minimization and is termed PCA-NCRM for short. Different from most existing PCA methods, which learn the linear transformations by minimizing the recovery errors between the recovered data and the original data in the least squared sense, our model adopts the monotonically non-decreasing concave function to enhance the ability of model in distinguishing correct samples and outliers. To be specific, PCA-NCRM enlarges the attention to samples with smaller recovery errors and diminishes the attention to samples with larger recovery errors at the same time. The proposed minimization problem can be efficiently addressed by employing an iterative re-weighting optimization. Experimental results on several datasets show the effectiveness of our model.
Keyword ：
Adaptation models Adaptation models Dimensionality reduction Dimensionality reduction High dimensional data High dimensional data Iterative algorithms Iterative algorithms Iterative re-weighting optimization Iterative re-weighting optimization Lagrangian functions Lagrangian functions Minimization Minimization Optimization Optimization Principal component analysis Principal component analysis principal component analysis (PCA) principal component analysis (PCA) Robustness Robustness Signal processing algorithms Signal processing algorithms unsupervised dimensionality reduction unsupervised dimensionality reduction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Qinghai , Zhuang, Yixin . Non-Decreasing Concave Regularized Minimization for Principal Component Analysis [J]. | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 : 486-490 . |
| MLA | Zheng, Qinghai et al. "Non-Decreasing Concave Regularized Minimization for Principal Component Analysis" . | IEEE SIGNAL PROCESSING LETTERS 32 (2025) : 486-490 . |
| APA | Zheng, Qinghai , Zhuang, Yixin . Non-Decreasing Concave Regularized Minimization for Principal Component Analysis . | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 , 486-490 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In real-world scenarios, missing views is common due to the complexity of data collection. Therefore, it is inevitable to classify incomplete multi-view data. Although substantial progress has been achieved, there are still two challenging problems with incomplete multi-view classification: (1) Simply ignoring these missing views is often ineffective, especially under high missing rates, which can lead to incomplete analysis and unreliable results. (2) Most existing multi-view classification models primarily focus on maximizing consistency between different views. However, neglecting specific-view information may lead to decreased performance. To solve the above problems, we propose a novel framework called Trusted Cross-View Completion (TCVC) for incomplete multi-view classification. Specifically, TCVC consists of three modules: Cross-view Feature Learning Module (CVFL), Imputation Module (IM) and Trusted Fusion Module (TFM). First, CVFL mines specific- view information to obtain cross-view reconstruction features. Then, IM restores the missing view by fusing cross-view reconstruction features with weights, guided by uncertainty-aware information. This information is the quality assessment of the cross-view reconstruction features in TFM. Moreover, the recovered views are supervised by cross-view neighborhood-aware. Finally, TFM effectively fuses complete data to generate trusted classification predictions. Extensive experiments show that our method is effective and robust.
Keyword ：
Cross-view feature learning Cross-view feature learning Incomplete multi-view classification Incomplete multi-view classification Uncertainty-aware Uncertainty-aware
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhou, Liping , Chen, Shiyun , Song, Peihuan et al. Trusted Cross-view Completion for incomplete multi-view classification [J]. | NEUROCOMPUTING , 2025 , 629 . |
| MLA | Zhou, Liping et al. "Trusted Cross-view Completion for incomplete multi-view classification" . | NEUROCOMPUTING 629 (2025) . |
| APA | Zhou, Liping , Chen, Shiyun , Song, Peihuan , Zheng, Qinghai , Yu, Yuanlong . Trusted Cross-view Completion for incomplete multi-view classification . | NEUROCOMPUTING , 2025 , 629 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
We tackle the problem of single-shape 3D generation, aiming to synthesize diverse and plausible shapes conditioned on a single input exemplar. This task is challenging due to the absence of dataset-level variation, requiring models to internalize structural patterns and generate novel shapes from limited local geometric cues. To address this, we propose a unified framework combining geometry-aware representation learning with a multiscale diffusion process. Our approach centers on a triplane autoencoder enhanced with a spatial pattern predictor and attention-based feature fusion, enabling fine-grained perception of local structures. To preserve structural coherence during generation, we introduce a soft feature distribution alignment loss that aligns features between input and generated shapes, balancing fidelity and diversity. Finally, we adopt a hierarchical diffusion strategy that progressively refines triplane features from coarse to fine, stabilizing training and improving quality. Extensive experiments demonstrate that our method produces high-fidelity, structurally consistent, and diverse shapes, establishing a strong baseline for single-shape generation.
Keyword ：
3D representation 3D representation Diffusion model Diffusion model Shape generation Shape generation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Hongliang , Zheng, Qinghai , Yu, Yuanlong et al. Geometry-aware triplane diffusion for single shape generation with feature alignment [J]. | COMPUTERS & GRAPHICS-UK , 2025 , 132 . |
| MLA | Weng, Hongliang et al. "Geometry-aware triplane diffusion for single shape generation with feature alignment" . | COMPUTERS & GRAPHICS-UK 132 (2025) . |
| APA | Weng, Hongliang , Zheng, Qinghai , Yu, Yuanlong , Zhuang, Yixin . Geometry-aware triplane diffusion for single shape generation with feature alignment . | COMPUTERS & GRAPHICS-UK , 2025 , 132 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In real-world scenarios, multi-view data usually contain missing or incomplete samples due to factors such as technical limitations and privacy issues during data collection or transmission. To alleviate this problem, Incomplete Multi-View Clustering (IMVC) has attracted increasing attention. Most existing IMVC methods still suffer from the following problems: (1) They do not make full use of structural relationship information of multi-view data to deal with missing values; (2) They face the challenge of maintaining the integrity of the original data and effectively avoiding error propagation when dealing with missing data; (3) They excel at deriving shared representations across multiple views but often overlook the uncertainty in clustering assignments within each view, resulting in increased category ambiguity. To address these issues, we propose a novel method, Relationship Completion for Incomplete Multi-View Clustering. Specifically, we design a novel relationship completion module to solve the missing value problem and obtain excellent relation graph features by directly completing the relationships of the missing views, ensuring the integrity of the original data and effectively mitigating the errors introduced during the completion process. We exploit multi-view complementary information through attention layer fusion and high-confidence bootstrapping. Semantic contrast learning and multi-view label distribution learning are introduced to further exploit multi-view consistent information. Extensive experiments with state-of-the-art methods on multiple real datasets demonstrate the effectiveness and superiority of the proposed method.
Keyword ：
Graph neural networks Graph neural networks Incomplete multi-view clustering Incomplete multi-view clustering Relationship completion Relationship completion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Minghong , Zhu, Jihua , Yan, Wenbiao et al. Relationship completion for incomplete multi-view clustering [J]. | NEURAL NETWORKS , 2025 , 191 . |
| MLA | Wu, Minghong et al. "Relationship completion for incomplete multi-view clustering" . | NEURAL NETWORKS 191 (2025) . |
| APA | Wu, Minghong , Zhu, Jihua , Yan, Wenbiao , Chen, Bin , Zheng, Qinghai . Relationship completion for incomplete multi-view clustering . | NEURAL NETWORKS , 2025 , 191 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi -view clustering leverages diverse information sources for unsupervised clustering. While existing methods primarily focus on learning a fused representation matrix, they often overlook the impact of private information and noise. To overcome this limitation, we propose a novel approach, the Multi -view Semantic Consistency based Information Bottleneck for Clustering (MSCIB). Our method emphasizes semantic consistency to enhance the information bottleneck learning process across different views. It aligns multiple views in the semantic space, capturing valuable consistent information from multi -view data. The learned semantic consistency improves the ability of the information bottleneck to precisely distinguish consistent information, resulting in a more discriminative and unified feature representation for clustering. Experimental results on diverse multi -view datasets demonstrate that MSCIB achieves state-of-the-art performance. In comparison with the average performance of the other contrast algorithms, our approach exhibits a notable improvement of at least 4%.
Keyword ：
Contrastive clustering Contrastive clustering Information bottleneck Information bottleneck Multi-view clustering Multi-view clustering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yan, Wenbiao , Zhou, Yiyang , Wang, Yifei et al. Multi-view Semantic Consistency based Information Bottleneck for Clustering [J]. | KNOWLEDGE-BASED SYSTEMS , 2024 , 288 . |
| MLA | Yan, Wenbiao et al. "Multi-view Semantic Consistency based Information Bottleneck for Clustering" . | KNOWLEDGE-BASED SYSTEMS 288 (2024) . |
| APA | Yan, Wenbiao , Zhou, Yiyang , Wang, Yifei , Zheng, Qinghai , Zhu, Jihua . Multi-view Semantic Consistency based Information Bottleneck for Clustering . | KNOWLEDGE-BASED SYSTEMS , 2024 , 288 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
