检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Du, Jia-Run Lin, Kun-Yu Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University China

To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for unseen categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposallevel objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the categoryagnostic dynamic information of actions. Besides, we introduce a Static- Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively. The code is available at https://***/Run542968/GAP. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Generating Anomalies for Video Anomaly Detection with Prompt-based Feature Mapping

Generating Anomalies for Video Anomaly Detection with Prompt...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zuhao Liu Xiao-Ming Wu Dian Zheng Kun-Yu Lin Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Anomaly detection in surveillance videos is a challenging computer vision task where only normal videos are available during training. Recent work released the first virtual anomaly detection dataset to assist real-world detection. However, an anomaly gap exists because the anomalies are bounded in the virtual dataset but unbounded in the real world, so it reduces the generalization ability of the virtual dataset. There also exists a scene gap between virtual and real scenarios, including scene-specific anomalies (events that are abnormal in one scene but normal in another) and scene-specific attributes, such as the viewpoint of the surveillance camera. In this paper, we aim to solve the problem of the anomaly gap and scene gap by proposing a prompt-based feature mapping framework (PFMF). The PFMF contains a mapping network guided by an anomaly prompt to generate unseen anomalies with unbounded types in the real scenario, and a mapping adaptation branch to narrow the scene gap by applying domain classifier and anomaly classifier. The proposed framework outperforms the state-of-the-art on three benchmark datasets. Extensive ablation experiments also show the effectiveness of our framework design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Antisymmetric planar Hall effect in rutile oxide films induced by the Lorentz force

引用

Science Bulletin 2024年第15期69卷 2362-2369页

作者： Yongwei Cui Zhaoqing Li Haoran Chen Yunzhuo Wu Yue Chen Ke Pei Tong Wu Nian Xie Renchao Che Xuepeng Qiu Yi Liu Zhe Yuan Yizheng Wu Department of Physics State Key Laboratory of Surface PhysicsFudan UniversityShanghai 200433China Institute for Nanoelectronic Devices and Quantum Computing Fudan UniversityShanghai 200433China Interdisciplinary Center for Theoretical Physics and Information Sciences Fudan UniversityShanghai 200433China Center for Advanced Quantum Studies and Department of Physics Beijing Normal UniversityBeijing 100875China Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative MaterialsAcademy for Engineering&TechnologyFudan UniversityShanghai 200438China Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology School of Physics Science and EngineeringTongji UniversityShanghai 200092China Zhejiang Laboratory Hangzhou 311100China Shanghai Research Center for Quantum Sciences Shanghai 201315China Shanghai Key Laboratory of Metasurfaces for Light Manipulation Fudan UniversityShanghai 200433China

The conventional Hall effect is linearly proportional to the field component or magnetization component perpendicular to a film. Despite the increasing theoretical proposals on the Hall effect to the in-plane field or magnetization in various special systems induced by the Berry curvature, such an unconventional Hall effect has only been experimentally reported in Weyl semimetals and in a heterodimensional superlattice. Here, we report an unambiguous experimental observation of the antisymmetric planar Hall effect(APHE) with respect to the in-plane magnetic field in centrosymmetric rutile RuO_(2) and IrO_(2) single-crystal films. The measured Hall resistivity is found to be linearly proportional to the component of the applied in-plane magnetic field along a particular crystal axis and to be independent of the current direction or temperature. Both the experimental observations and theoretical calculations confirm that the APHE in rutile oxide films is induced by the Lorentz force. Our findings can be generalized to ferromagnetic materials for the discovery of anomalous Hall effects and quantum anomalous Hall effects induced by in-plane magnetization. In addition to significantly expanding knowledge of the Hall effect, this work opens the door to explore new members in the Hall effect family.

关键词： Antisymmetric planar Hall effect Lorentz force Rutile oxide films Crystal symmetry

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Cross-stage Regional Contrastive Learning for Object Detection

Self-supervised Cross-stage Regional Contrastive Learning fo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Junkai Yan Lingxiao Yang Yipeng Gao Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Cross-stage object similarity is a vital property of generic supervised object detectors, which maintains similar feature responses to the same object across feature maps of different intermediate stages of the backbone network. Since an object can be predicted by multiple stages, this similarity is beneficial for accurate object classification and localization. Inspired by this property, we introduce Cross-stage regional Contrastive Learning (CrossCL) to learn the cross-stage object similarity during the model pre-training. Since labels are unavailable in self-supervised learning, we treat the regions sharing the same position in different stages as the same object and constrain them to have similar feature responses across stages to achieve cross-stage object similarity. The learned feature representations of CrossCL share a similar property with supervised detectors, thus showing strong transfer capability to object detection tasks. Besides, we also provide in-depth discussions, ablation studies, and visualizations to understand better how CrossCL works. Code is available at https://***/yanjk3/CrossCL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

arXiv

引用

arXiv 2025年

作者： Xiao, Junjin Zhang, Qing Nie, Yonewei Zhu, Lei Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China South China University of Technology China China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject optimization. Unlike previous methods that typically struggle with sparse views with few overlappings and are less effective in reconstructing complex human geometry, the proposed method enables robust reconstruction in such challenging conditions. Our key idea is to lift SMPL vertices to dense and reliable 3D prior points representing accurate human body geometry, and then regress human Gaussian parameters based on the points. To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians. To enhance the ability to capture high-frequency details, we further render depth maps from the coarse 3D Gaussians to help regress fine-grained pixel-wise Gaussians. Experiments on several benchmark datasets demonstrate that our method outperforms state-of-the-art methods in novel view synthesis and cross-dataset generalization. Our code is available at https: //***/iSEE-laboratory/RoGSplat. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Diversifying Spatial-Temporal Perception for Video Domain Generalization

arXiv

引用

arXiv 2023年

作者： Lin, Kun-Yu Du, Jia-Run Gao, Yipeng Zhou, Jiaming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Video domain generalization aims to learn generalizable video classification models for unseen target domains by training in a source domain. A critical challenge of video domain generalization is to defend against the heavy reliance on domain-specific cues extracted from the source domain when recognizing target videos. To this end, we propose to perceive diverse spatial-temporal cues in videos, aiming to discover potential domain-invariant cues in addition to domain-specific cues. We contribute a novel model named Spatial-Temporal Diversification Network (STDN), which improves the diversity from both space and time dimensions of video data. First, our STDN proposes to discover various types of spatial cues within individual frames by spatial grouping. Then, our STDN proposes to explicitly model spatial-temporal dependencies between video contents at multiple space-time scales by spatial-temporal relation modeling. Extensive experiments on three benchmarks of different types demonstrate the effectiveness and versatility of our approach. © 2023, CC BY-SA.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

A survey of coverage-guided greybox fuzzing with deep neural models

引用

Information and Software Technology 2025年 186卷

作者： Qiu, Junyang Jiang, Yupeng Miao, Yuantian Luo, Wei Pan, Lei Zheng, Xi State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214123 China School of Computing Macquarie University Sydney 2109 NSW Australia School of Information and Physical Sciences University of Newcastle Newcastle 2308 NSW Australia School of Information Technology Deakin University Melbourne 3125 VIC Australia

Coverage-guided greybox fuzzing (CGF) has emerged as a powerful technique for software vulnerability detection, yet traditional techniques often struggle with the increasing complexity of modern software systems and the vastness of input spaces. Deep neural networks (DNNs) have begun to fundamentally transform CGF by addressing these limitations through automated feature extraction, adaptive input generation, and intelligent path prioritization. However, despite these advancements, critical gaps persist in understanding the state-of-the-art landscape. Existing studies often lack rigorous benchmarks to evaluate scalability and generalizability, fail to address the interpretability of neural-guided decisions, and overlook the integration of emerging paradigms such as large language models (LLMs) and neurosymbolic reasoning. This survey systematically bridges these gaps by providing a comprehensive taxonomy of DNN-driven CGF techniques, analyzing their strengths and limitations across key fuzzing stages—seed generation, selection, and mutation. We find that although DNNs have significantly improved fuzzing efficiency, challenges such as semantically invalid seeds, high computational overhead, and limited cross-domain adaptability remain unresolved. Most importantly, we identify two transformative directions with the potential to redefine CGF: (1) LLM-powered fuzzing, which combines generative AI with domain-specific fine-tuning to produce context-aware inputs;and (2) neurosymbolic integration, which merges the precision of symbolic execution with the scalability of neural networks to tackle path explosion. By synthesizing these insights, this survey not only clarifies the state-of-the-art but also outlines a roadmap for developing robust, explainable, and widely applicable intelligent fuzzers. The future of CGF lies in hybrid models that integrate data-driven learning with formal methods, paving the way for autonomous vulnerability discovery in an era of increasingly c

关键词： Code coverage Deep learning Greybox fuzzing Large language models Software vulnerability

来源：评论

学校读者我要写书评

暂无评论

A Selection Strategy for Network Security Defense Based on a Time Game Model

A Selection Strategy for Network Security Defense Based on a...

引用

Digital Society and Intelligent Systems (DSInS), International Conference on

作者： Pengyu Sun Hengwei Zhang Junqiang Ma Chenwei Li Yan Mi Jindong Wang State Key Laboratory of Mathematical Engineering and Advanced Computing Key Laboratory of Information Security of Henan Provincial Zhengzhou China

ISBN: (纸本)9781665406314

Current network assessment models often ignore the impact of attack-defense timing on network security, making it difficult to characterize the dynamic game of attack-defense effectively. To effectively manage the network security risks and reduce potential losses, in this article, we propose a selection strategy for network defense based on a time game model. By analyzing the attack-defense status by analogy with the SIR infectious disease model, construction of an optimal defense strategy model based on time game, and calculation of the Nash equilibrium of the the attacker and the defender under different strategies, we can determine an optimal defense strategy. With the Matlab simulation, this strategy is verified to be effective.

关键词： Analytical models Heuristic algorithms Games Network security Numerical simulation Nash equilibrium Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Timing Strategy for Active Detection of APT Attack Based on FlipIt Model and Q-learning Method

Timing Strategy for Active Detection of APT Attack Based on ...

引用

Digital Society and Intelligent Systems (DSInS), International Conference on

作者： Zhilin Liu Hengwei Zhang Pengyu Sun Yan Mi Xiaoning Zhang Jindong Wang State Key Laboratory of Mathematical Engineering and Advanced Computing Key Laboratory of Information Security of Henan Provincial Zhengzhou China

ISBN: (纸本)9781665406314

At present, APT attack detection mainly focuses on the specific realization of detection technology, and there is little research on the timing strategy for active detection of APT attack. This paper focuses on the problem of APT dynamic detection with timing decision intelligence. We use the FlipIt game model and reinforcement learning method of Q-learning algorithm, consider the APT attack events as an exponentially distributed random process, and the defender using the attacker’s last move time (LM-defender) to learn his optimal timing strategy using Q-Learning algorithm. The defender's reinforcement learning mechanism for the timing of the APT attack action and outputs its timing selection strategy. Simulation experiments show that compared with the existing greedy algorithm, the timing strategy based on the Q-Learning algorithm does not require the attacker's prior information under the premise, it can achieve a higher average benefit than the greedy strategy. This result provides a theoretical reference for the design of timing strategy to defend APT attack intelligently and efficient.

关键词： Greedy algorithms Adaptation models State feedback Q-learning Adaptive systems Heuristic algorithms Games

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：