检索结果-内蒙古大学图书馆

International Electron Devices Meeting (IEDM)

作者： Linlin Cai Yutao Chen Haoyu Zhang Jianwen Lin Binyu Yin Wangyong Chen School of Microelectronics Science and Technology Sun Yat-sen University Guangzhou China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

Electromigartion (EM) reliability of backside power delivery network (BSPDN) using three kinds of techniques (BPR, TSVM and BSC) is comprehensively investigated by proposed electro-thermal-stress fully coupled EM simulation method. The physical behaviors of metal atom migration, vacancy generation and void nucleation are reproduced to offer the understanding of microscopic void evolutions. The obtained position of EM failure and resistance degradation show a well agreement with the experiments in different metals. By studying the time to failure (TTF) of various BSPDNs connected to power lines (GND, VDD) with alternative metal materials (W, Ru, Mo), valuable insights can be gained to mitigate potential failure risks and enhance the EM reliability of advanced interconnects technology. The tradeoffs of power-performance-area-reliability (PPAR) are predicted in different BSPDNs at N2 node.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind

arXiv

引用

arXiv 2024年

作者： Mao, Yuanyuan Lin, Xin Ni, Qin He, Liang Shanghai Key Laboratory of Multidimensional Information Processing ECNU Shanghai China Department of Computer Science and Technology East China Normal University China Key Laboratory of Multilingual Education with AI Shanghai International Studies University China

As a foundational component of cognitive intelligence, theory of mind (ToM) can make AI more closely resemble human thought processes, thereby enhancing their interaction and collaboration with human. In particular, it can significantly improve a model’s comprehension of videos in complex scenes. However, current video question answer (VideoQA) datasets focus on studying causal reasoning within events, few of them genuinely incorporating human ToM. Consequently, there is a lack of development in ToM reasoning tasks within the area of VideoQA. This paper presents BDIQA, the first benchmark to explore the cognitive reasoning capabilities of VideoQA models in the context of ToM. BDIQA is inspired by the cognitive development of children’s ToM and addresses the current deficiencies in machine ToM within datasets and tasks. Specifically, it offers tasks at two difficulty levels, assessing Belief, Desire and Intention (BDI) reasoning in both simple and complex scenarios. We conduct evaluations on several mainstream methods of VideoQA and diagnose their capabilities with zero-shot, few-shot and supervised learning. We find that the performance of pre-trained models on cognitive reasoning tasks remains unsatisfactory. To counter this challenge, we undertake thorough analysis and experimentation, ultimately presenting two guidelines to enhance cognitive reasoning derived from ablation analysis. © 2024, CC0.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose 39

DanceFix: An Exploration in Group Dance Neatness Assessment ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Huangbiao Ke, Xiao Wu, Huanqi Xu, Rui Li, Yuezhou Xu, Peirong Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

ISBN: (纸本)157735897X

The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix proposes a bidirectional spatial-temporal context optical flow correction (BOFC) method. This approach leverages the consistency and complementarity of motion information between two modalities: optical flow, which excels at pixel capture, and lightweight skeleton data. It enables the extraction of pixel-level motion changes and the correction of abnormal skeleton data. Furthermore, we propose a part-level dance dataset (Dancer Parts) and part-level motion feature extraction based on task decoupling (PETD). This aims to decouple complex whole-body parts tracking into fine-grained limb-level motion extraction, enhancing the confidence of temporal information and the accuracy of correction for abnormal data. Finally, we present the DNV dataset, which simulates fully neat group dance scenes and provides reliable labels and validation methods for the newly introduced group dance neatness assessment (GDNA). To the best of our knowledge, this is the first work to develop quantitative criteria for assessing limb and joint neatness in group dance. We conduct experiments on DNV and video-based public JHMDB datasets. Our method effectively corrects abnormal skeleton points, flexibly embeds, and improves the accuracy of existing pose estimation algorithms. 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

Texture Mapping Based on Planar Projection Mapping in fully analytic polygon-based computer generated holography

Texture Mapping Based on Planar Projection Mapping in fully ...

引用

Frontiers in Optics, FiO 2022

作者： Fu, Qingyang Zhang, Yaping Zhang, Bing Poon, Ting-Chung Yunnan Provincial Key Laboratory of Modern Information Optics Kunming University of Science and Technology Yunnan Kunming650500 China Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States

We propose the use of planar projection mapping to texture fully analytic 3D affine transformed computer-generated holograms. Simulation results show that this is an effective texture mapping method. © 2022 The A...

ISBN: (纸本)9781557528209

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

arXiv

引用

arXiv 2023年

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lin, Yuzhen Song, Wentang Li, Bin Li, Yuezun Ni, Jiangqun Chen, Han Li, Qiushi Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security SZU-AFS Joint Innovation Center for AI Technology Shenzhen University Shenzhen China College of Computer Science and Technology Ocean University of China Qingdao China School of Cyber Science and Technology Sun Yat-Sen University Department of New Networks Peng Cheng Laboratory Shenzhen China

Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from unseen datasets and created by unseen methods. In this work, we present a novel general deepfake detection method, called Curricular Dynamic Forgery Augmentation (CDFA), which jointly trains a deepfake detector with a forgery augmentation policy network. Unlike the previous works, we propose to progressively apply forgery augmentations following a monotonic curriculum during the training. We further propose a dynamic forgery searching strategy to select one suitable forgery augmentation operation for each image varying between training stages, producing a forgery augmentation policy optimized for better generalization. In addition, we propose a novel forgery augmentation named self-shifted blending image to simply imitate the temporal inconsistency of deepfake generation. Comprehensive experiments show that CDFA can significantly improve both cross-datasets and cross-manipulations performances of various naive deepfake detectors in a plug-and-play way, and make them attain superior performances over the existing methods in several benchmark datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Multilingual Pre-training Model-Assisted Contrastive Learning Neural Machine Translation

Multilingual Pre-training Model-Assisted Contrastive Learnin...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shuo Sun Hong–xu Hou Zong–heng Yang Yi–song Wang National& Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science Inner Mongolia University Hohhot China

Since pre-training and fine-tuning have been a successful paradigm in Natural Language processing (NLP), this paper adopts the SOTA pre-training model-CeMAT as a strong assistant for low-resource ethnic language translation tasks. Aiming at the exposure bias problem in the fine-tuning process, we use the contrastive learning framework and propose a new contrastive examples generation method, which uses self- generated predictions as contrastive examples to expose the model to errors during inference. Moreover, in order to effectively utilize the limited bilingual data in low-resource tasks, this paper proposes a dynamic training strategy to fine-tune the model, and refines the model step by step by taking word embedding norm and uncertainty as the criteria of evaluate data and model respectively. Experimental results demonstrate that our method significantly improves the quality compared to the baselines, which fully verifies the effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-rank matrix recovery with total generalized variation for defending adversarial examples

引用

Frontiers of information technology & Electronic Engineering 2024年第3期25卷 432-445页

作者： Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng School of Science Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China Institute of Big Data Modeling and Technology Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image *** advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural ***,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its *** our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery *** the proposed model,TGV is used to better reconstruct texture information without *** reweighted nuclear norm and Li-norm can enhance the global structure ***,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the *** solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of *** results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关键词： Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example

来源：评论

学校读者我要写书评

暂无评论

A Decentralized Federated Learning Framework with Enhanced Privacy and Optimized Fairness

A Decentralized Federated Learning Framework with Enhanced P...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Lianhai Wang Qi Li Shujiang Xu Shuhui Zhang Wei Shao Qizheng Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan PR China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan PR China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Federated Learning is a widely used distributed machine learning framework that allows clients to collaboratively train a global model by uploading local gradients while keeping data stored locally, thus protecting user privacy. However, attackers can still infer local data from gradients. Recently, integrating differential privacy into FL has become a popular approach to ensure strong privacy guarantees. This paper proposes a Decentralized Federated Learning Framework with Enhanced Privacy and Optimized Fairness (DFL-EPOF). First, noise is added to local parameters before uploading, and a local differential privacy mechanism ensures data privacy. An adaptive privacy budget allocation strategy, based on data sensitivity, dynamically controls noise levels to balance privacy protection and model accuracy. Second, a weighted aggregation method based on clients' data volume, trustworthiness, and participation frequency is used to optimize fairness, ensuring balanced contributions. Finally, a decentralized blockchain-based architecture is implemented to enhance transparency and immutability, ensuring reliable model updates and data transmission. Experimental results show that DFL-EPOF improves privacy protection, fairness, and system robustness, balancing privacy and accuracy effectively.

关键词： Privacy Differential privacy Accuracy Sensitivity Systematics Federated learning Data models Robustness Blockchains Protection

来源：评论

学校读者我要写书评

暂无评论

Multi-scale fusion clustering algorithm for urban travel features 3

Multi-scale fusion clustering algorithm for urban travel fea...

引用

2023 3rd International Conference on Intelligent Traffic Systems and Smart City, ITSSC 2023

作者： Zhang, Zixiang Zhao, Zhilong Deng, Jiaming Zhao, Yingying Xu, Tao Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Key Laboratory of Geographical Information Science Ministry of Education East China Normal University Shanghai200241 China School of Computer and Information Engineering Henan University Kaifeng475004 China International Education College Henan University Zhengzhou450046 China Henan Technology Innovation Center of Spatio-Temporal Big Data Henan University Zhengzhou450046 China Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

ISBN: (纸本)9781510672963

Urban travel data typically encompass various temporal and spatial scales and features. Nonetheless, existing traffic travel feature analysis often focuses on a single spatial scale, which may overlook crucial information and hinder features at different scales. Consequently, this could reduce the accuracy of travel pattern recognition. To solve this problem, we introduce a multi-scale fusion transformation algorithm. In our approach, we first establish a multi-level taxi travel data grid system. Then, we apply the I-Clique clustering algorithm to perform grid clustering at each level of the system to identify taxi travel feature regions of different scales. Subsequently, a multi-scale fusion pyramid model is constructed utilizing the acquired travel feature regions at various scales. Finally, we determine the transformation relationships between scales in the pyramid model, enabling the identification of travel feature areas across both known and unknown scales. This approach facilitates the recognition of travel features within cities at any scale. Experimental results demonstrate that the multi-scale fusion transformation algorithm enhances our understanding of spatial aggregation patterns and the hierarchical structure of geographical entities, offering a novel approach for multi-scale urban traffic analysis. © 2024 SPIE. All rights reserved.

关键词： Clustering algorithms

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：