检索结果-内蒙古大学图书馆

One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing

IEEE Transactions on Multimedia 2025年

作者： Ji, Yuzhu Zheng, Chuanxia Cham, Tat-Jen Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China University of Oxford Department of Engineering Science Oxford United Kingdom Nanyang Technological University College of Computing and Data Science Singapore Singapore

Human motion transfer aims at animating a static source image with a driving video. While recent advances in one-shot human motion transfer have led to significant improvement in results, it remains challenging for methods with 2D body landmarks, skeleton and semantic mask to accurately capture correspondences between source and driving poses due to the large variation in motion and articulation complexity. In addition, the accuracy and precision of DensePose degrade the image quality for neural-rendering-based methods. To address the limitations and by both considering the importance of appearance and geometry for motion transfer, in this work, we proposed a unified framework that combines multi-scale feature warping and neural texture mapping to recover better 2D appearance and 2.5D geometry, partly by exploiting the information from DensePose, yet adapting to its inherent limited accuracy. Our model takes advantage of multiple modalities by jointly training and fusing them, which allows it to robust neural texture features that cope with geometric errors as well as multi-scale dense motion flow that better preserves appearance. Experimental results with full and half-view body video datasets demonstrate that our model can generalize well and achieve competitive results, and that it is particularly effective in handling challenging cases such as those with substantial self-occlusions. © 1999-2012 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Neighbor Relations Matter in Video Scene Detection

Neighbor Relations Matter in Video Scene Detection

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiawei Tan Hongxing Wang Jiaxin Li Zhilong Ou Zhangbin Qian Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video scene detection aims to temporally link shots for obtaining semantically compact scenes. It is essential for this task to capture scene-distinguishable affinity among shots by similarity assessment. However, most methods relies on ordinary shot-to-shot similarities, which may inveigle similar shots into being linked even though they are from different scenes, and meanwhile hinder dissimilar shots from being blended into a complete scene. In this paper, we propose NeighborNet to inject shot contexts into shot-to-shot similarities through carefully exploring the relations between semantic/temporal neighbors of shots over a local time period. In this way, shot-to-shot similarities are remeasured as semantic/temporal neighbor-aware similarities so that NeighborNet can learn context embedding into shot features using graph convolutional network. As a result, not only do the learned shot features suppress the affinity among similar shots from different scenes, but they also promote the affinity among dissimilar shots in the same scene. Experimental results on public benchmark datasets show that our proposed NeighborNet yields substantial improvements in video scene detection, especially outperforms released state-of-the-arts by at least 6% in Average Precision (AP). The code is available at https://***/ExMorgan-Alter/NeighborNet.

关键词： Learning systems Computer vision Codes Graph convolutional networks Image edge detection Semantics Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

FPGA-Optimized Hardware Accelerator for Fast Fourier Transform and Singular Value Decomposition in AI

FPGA-Optimized Hardware Accelerator for Fast Fourier Transfo...

引用

computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Hong Ding Chia Chao Kang SuYang Xi Zehang Liu Xuan Zhang Yi Ding School of Electrical Engineering and Artificial Intelligence Xiamen University Malaysia Sepang Malaysia School of Computing and Data Science Xiamen University Malaysia Sepang Malaysia School of Economics and Management Xiamen University Malaysia Sepang Malaysia

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

This research introduces an FPGA-based hardware accelerator to optimize the Singular Value Decomposition (SVD) and Fast Fourier transform (FFT) operations in AI models. The proposed design aims to improve processing speed and reduce computational latency. Through experiments, the paper validates the performance benefits of the hardware accelerator and shows how well it handles FFT and SVD operations. With its strong security and durability, the accelerator design achieves significant speedups over software implementations based on its modules for data flow control, watermark embedding, FFT and SVD.

关键词： Technological innovation Fast Fourier transforms Flow production systems Computational modeling Education Watermarking Software Artificial intelligence Hardware acceleration Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Cursive Hand writing Recognition Using Neural Networks with VGG-16

Cursive Hand writing Recognition Using Neural Networks with ...

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Anushka Anil Rangari Swagat Das Rajeswari D Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India

Recognition of cursive handwritten text from photographs is a method for finding handwritten text. Identification is difficult because every author has a distinctive writing style. The proposed work uses cutting-edge technologies including RNN, KNN, MLP, and CRNN twith VGG16 to push the boundaries of character and handwriting recognition. Additionally, it compares neural networks to CNNwith VGG16 and finds that neural networks are more accurate. In the first stage, image acquisition, the scanned image is acquired along with its normalization, feature extraction, and segmentation. Additionally, it combines with the most effective feature extraction technique to improve the accuracy of our model. It also compares the accuracy with six uniquepretreat. approach, which are image segmentation image data generator data augmentation closed loop pre-processing, sigmoid Stretching and geometric *** provides the highest accuracy (98.36%) when using data augmentation. CNN has the highest accuracy (95.25%) when using picture segmentation. The third experiment's results for the image data generator show that CNN produced the best results (92.47%), while the highest model, RNN, gave closed loop processing accuracy of 92.20%. a change in geometry KNN has the highest accuracy at 95.39%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proving Linearizability of Concurrent Queues

引用

Journal of Computers (Taiwan) 2024年第5期35卷 91-103页

作者： Peng, Jie Wen, Tangliu Jiang, Dongming Department of Information Engineering Gannan University of Science and Technology Ganzhou China Ganzhou Cloud Computing and Big Data Research Center Ganzhou China School of Big Data Jiangxi Science & Technology Normal University Nanchang China

Linearizability is a commonly accepted correctness criterion for concurrent data structures. Concurrent queues are among the most fundamental concurrent data structures. In this paper, we present necessary and sufficient conditions for proving linearizability of concurrent queues, which make use of linearization of dequeue operations. The verification conditions intuitively express the "FIFO" semantics of concurrent queues and can be verified just by reasoning about the happened-before order of operations. We have successfully applied the proof technique to prove several challenging concurrent queues. We believe that our proof technique can be extended to the concurrent data structures which have the ordering requirements when their elements are removed. © 2024 Codon Publications. All rights reserved.

关键词： data structures

来源：评论

学校读者我要写书评

暂无评论

Multi-Turn Jailbreaking Large Language Models via Attention Shifting 39

Multi-Turn Jailbreaking Large Language Models via Attention ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Xiaohu Mo, Fan Wen, Ming Gu, Tu Zheng, Huadi Jin, Hai Shi, Jie School of Cyber Science and Engineering Huazhong University of Science and Technology (HUST) China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab School of Computer Science and Technology HUST China JinYinHu Laboratory China Huawei International China

ISBN: (纸本)157735897X

Large Language Models (LLMs) have achieved significant performance in various natural language processing tasks but also pose safety and ethical threats, thus requiring red teaming and alignment processes to bolster their safety. To effectively exploit these aligned LLMs, recent studies have introduced jailbreak attacks based on multi-turn dialogues. These attacks aim to prompt LLMs to generate harmful or biased content by guiding them through contextual content. However, the underlying reasons for the effectiveness of multi-turn jailbreaks remain unclear. Existing attacks often focus on optimizing queries and escalating toxicity to construct dialogues, lacking a thorough analysis of the inherent vulnerabilities of LLMs. In this paper, we first conduct an in-depth analysis of the differences between single-turn and multi-turn jailbreaks and find that successful multi-turn jailbreaks can effectively disperse the attention of LLMs on keywords associated with harmful behaviors, especially in historical responses. Based on this, we propose ASJA, a new multi-turn jailbreak approach by shifting the attention of LLMs, specifically by iteratively fabricating the dialogue history through a genetic algorithm to induce LLMs to generate harmful content. Extensive experiments on three LLMs and two datasets show that our approach surpasses existing approaches in jailbreak effectiveness, the stealth of jailbreak prompts, and attack efficiency. Our work emphasizes the importance of enhancing the robustness of LLMs’ attention mechanism in multi-turn dialogue scenarios for a better defense strategy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HYPERBOLIC HYPERGRAPH NEURAL NETWORKS FOR MULTI-RELATIONAL KNOWLEDGE HYPERGRAPH REPRESENTATION

arXiv

引用

arXiv 2024年

作者： Li, Mengfan Shi, Xuanhua Qiao, Chenqi Zhang, Teng Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

As Pseudo-label Free As Possible: Leveraging Adaptive Feature Generation for Sparsely Annotated Object Detection 39

As Pseudo-label Free As Possible: Leveraging Adaptive Featur...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yao, Shuilian Liu, Yu Jia, Qi Chen, Sihong Zhuo, Wei School of Software Technology DUT-RU International School of Information Science & Engineering Dalian University of Technology Dalian China AILab Tencent Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)157735897X

Compared to fully supervised object detection, training with sparse annotations typically leads to a decline in performance due to insufficient feature diversity. Existing sparsely annotated object detection (SAOD) methods often rely on pseudo-labeling strategies, but these pseudo-labels tend to introduce noise under extreme sparsity. To simultaneously avoid the impact of pseudo-label noise and enhance feature diversity, we propose a novel Adaptive Feature Generation (AdaptFG) model that generates features based on class names. This model integrates a pre-trained CLIP into a VAE-based feature generator, with its core innovation being an Adaptor that adaptively maps CLIP semantic embeddings to the object detector domain. Additionally, we introduce inter-class relationship reasoning in detector, which effectively mitigates misclassifications stemming from similar features. Extensive experimental results demonstrate that AdaptFG consistently outperforms state-of-the-art SAOD methods on the PASCAL VOC and MS COCO benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ethereum smart contract security research:survey and future research opportunities

引用

Frontiers of Computer Science 2021年第2期15卷 143-160页

作者： Zeli WANG Hai JIN Weiqi DAI Kim-Kwang Raymond CHOO Deqing ZOU National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabHubei Engineering Research Center on Big Data SecurityWuhan430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Blockchain has recently emerged as a research trend,with potential applications in a broad range of industries and *** particular successful Blockchain technology is smart contract,which is widely used in commercial settings(e.g.,high value financial transactions).This,however,has security implications due to the potential to financially benefit from a security incident(e.g.,identification and exploitation of a vulnerability in the smart contract or its implementation).Among,Ethereum is the most active and ***,in this paper,we systematically review existing research efforts on Ethereum smart contract security,published between 2015 and ***,we focus on how smart contracts can be maliciously exploited and targeted,such as security issues of contract program model,vulnerabilities in the program and safety consideration introduced by program execution *** also identify potential research opportunities and future research agenda.

关键词： smart contract security blockchain vulnerability unreliable data

来源：评论

学校读者我要写书评

暂无评论

Hybrid Semantic/Bit Communication Based Networking Problem Optimization

arXiv

引用

arXiv 2024年

作者： Xia, Le Sun, Yao Niyato, Dusit Zhang, Lan Zhang, Lei Imran, Muhammad Ali James Watt School of Engineering University of Glasgow Glasgow United Kingdom College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering Clemson University United States

This paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a novel and practical next-generation cellular network where two modes of semantic communication (SemCom) and conventional bit communication (BitCom) coexist, namely hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of message throughput for both SemCom and BitCom links. Next, we comprehensively develop a knowledge matching-aware two-stage tandem packet queuing model and theoretically derive the average packet loss ratio and queuing latency. Combined with several practical constraints, we then formulate a joint optimization problem for UA, MS, and BA to maximize the overall message throughput of HSB-Net. Afterward, we propose an optimal resource management strategy by employing a Lagrange primal-dual method and devising a preference list-based heuristic algorithm. Finally, numerical results validate the performance superiority of our proposed strategy compared with different benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency allocation

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：