检索结果-内蒙古大学图书馆

Precise Facial Landmark Detection by Reference Heatmap Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wan, Jun Liu, Jun Zhou, Jie Lai, Zhihui Shen, Linlin Sun, Hang Xiong, Ping Min, Wenwen The School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore The College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China College of Computer and Information Technology China Three Gorges University HuBei Yichang China The School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results. However, when the face image is suffering from large poses, heavy occlusions and complicated illuminations, they cannot learn discriminative feature representations and effective facial shape constraints, nor can they accurately predict the value of each element in the landmark heatmap, limiting their detection accuracy. To address this problem, we propose a novel Reference Heatmap Transformer (RHT) by introducing reference heatmap information for more precise facial landmark detection. The proposed RHT consists of a Soft Transformation Module (STM) and a Hard Transformation Module (HTM), which can cooperate with each other to encourage the accurate transformation of the reference heatmap information and facial shape constraints. Then, a Multi-Scale Feature Fusion Module (MSFFM) is proposed to fuse the transformed heatmap features and the semantic features learned from the original face images to enhance feature representations for producing more accurate target heatmaps. To the best of our knowledge, this is the first study to explore how to enhance facial landmark detection by transforming the reference heatmap information. The experimental results from challenging benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art methods in the literature. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

Provably Convergent Federated Trilevel Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

A Point-to-distribution Degeneracy Detection Factor for LiDAR SLAM using Local Geometric Models

学校读者我要写书评

暂无评论

A Point-to-distribution Degeneracy Detection Factor for LiDA...

IEEE International Conference on robotics and Automation (ICRA)

作者： Sehua Ji Weinan Chen Zerong Su Yisheng Guan Jiehao Li Hong Zhang Haifei Zhu Biomimetic and Intelligent Robotics Lab (BIRL) School of Electromechanical Engineer Guangdong University of Technology Guangzhou China JT-Innovation (Guangdong) Intelligent Technology Co. Ltd. Guangdong Key Laboratory of Modern Control Technology Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China College of Engineering South China Agricultural University China Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Limited by the working principles, LiDAR-SLAM systems suffer from the degeneration phenomenon in environments such as long corridors and tunnels, due to the lack of sufficient geometric features for frame-to-frame matching. The accuracy and sensitivity of existing degeneracy detection methods need to be further improved. In this paper, we propose a novel method for degeneracy detection using local geometric models based on point-to-distribution matching. To obtain an accurate description of local geometric models, an adaptive adjustment of voxel segmentation according to the point cloud distribution and density is designed. The codes of the proposed method is open-source and available at https://***/jisehua/***. Experiments with public datasets and self-build robots were conducted to evaluate the methods. The results exhibit that our proposed method achieves higher accuracy than the other existing approaches. Applying our proposed method is beneficial for improving the robustness of the LiDAR-SLAM systems.

关键词： Point cloud compression Accuracy Simultaneous localization and mapping Sensitivity Laser radar Geometric modeling Noise

A Detailed Analysis of Qualitative and Quantitative Factors in Realization of 6G Communication

学校读者我要写书评

暂无评论

A Detailed Analysis of Qualitative and Quantitative Factors ...

International Conference on Internet of Things: Systems, Management and Security

作者： Mohammad Alja’Afreh Ali Karime Sahel Alouneh Abdulmotaleb El Saddik Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) UAE School of Electrical Engineering and Computer Science University of Ottawa Canada Department of Electrical and Computer Engineering The Royal Military College of Canada Canada Cybersecurity Program College of Engineering AL AIN University UAE Computer Engineering Department German Jordanian University

Undoubtedly, the world has so far faced a pandemic which is reshaping daily lives and business activities. Even at current endemic stages, special focus on maintaining physical distancing norms for curbing the expeditious spread of the disease, many institutions, individuals and industries rely on communications networks or telecoms for ensuring service consistency to avoid complete termination of their business operations and other activities. This has put enormous pressure on mobile networks and communication systems thereby making the technology experts to think more about introducing rapid speed, vast coverage and high connectivity networks. The extensive application of fresh communication networks and enabling technologies have impelled the advent of 6G communication networks. As 6G is still in its inception phase, its complete realization requires a proper and high understanding of diverse quantitative and qualitative factors supporting its deployment. From this standpoint, this survey article intends to deeply explore 6G networks, their significance and prerequisites. This paper provides a succinct theoretical background of 6G technology, and reviews the diverse enabling technologies and existing works undertaken on core technologies. It explores the prevailing gaps in research for providing readers to gain information regarding challenges in perfect 6G network realization and implementation thus paving the road for a successful 6G vision.

关键词： 6G mobile communication Systematics Pandemics Roads Telecommunications Communication networks Security

Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

Fuzzy Positive Learning for Semi-Supervised Semantic Segment...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Pengchong Qiao Zhidan Wei Yu Wang Zhennan Wang Guoli Song Fan Xu Xiangyang Ji Chang Liu Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Department of Automation and BNRist Tsinghua University Beijing China

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and resort to exhausting informative semantics from multiple probably correct candidate labels. In this paper, we introduce Fuzzy Positive Learning (FPL) for accurate SSL semantic segmentation in a plug-and-play fashion, targeting adaptively encouraging fuzzy positive predictions and suppressing highly-probable negatives. Being conceptually simple yet practically effective, FPL can remarkably alleviate interference from wrong pseudo labels and progressively achieve clear pixel-level semantic discrimination. Concretely, our FPL approach consists of two main components, including fuzzy positive assignment (FPA) to provide an adaptive number of labels for each pixel and fuzzy positive regularization (FPR) to restrict the predictions of fuzzy positive categories to be larger than the rest under different perturbations. Theoretical analysis and extensive experiments on Cityscapes and VOC 2012 with consistent performance gain justify the superiority of our approach. Codes are provided in https://***/qpc1611094/FPL.

关键词：

A mutually beneficial approach to electricity network pricing in the presence of large amounts of solar power and community-scale energy storage

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sturmberg, Björn C. P. Shaw, M.E. Mediwaththe, C.P. Ransan-Cooper, H. Weise, B. Thomas, M. Blackhall, L. Battery Storage and Grid Integration Program School of Engineering College of Engineering and Computer Science The Australian National University

Electricity distribution networks that contain large photovoltaic solar systems can experience power flows between customers. These may create both technical and socio-economic challenges. This paper establishes how these challenges can be addressed through the combined deployment of Community-scale Energy Storage (CES) and local network tariffs. Our study simulates the operation of a CES under a range of local network tariff models, using current Australian electricity prices and current network prices as a reference. We assess the financial outcomes for solar and non-solar owning customers and the distribution network operator. We find that tariff settings exist that create mutual benefits for all stakeholders. Such tariffs all apply a discount of greater than 50% to energy flows within the local network, relative to regular distribution network tariffs. The policy implication of these findings is that the, historically contentious, issue of network tariff reform in the presence of local solar power generation can be resolved with a mutually beneficial arrangement of local network tariffs and CES. Furthermore, the challenge of setting appropriate tariffs is eased through clear and intuitive conditions on local network tariff pricing. © 2021, CC BY-NC-SA.

关键词： Solar power generation

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Jiangrong Xu, Qi Pan, Gang Chen, Badong Faculty of Electronic and Information Engineering Xi’an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Lab of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University China School of Computer Science Dalian University of Technology China

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based computation, Spiking Neural Networks (SNNs) have been developed to construct event-driven models that emulate this efficiency. Despite these advances, deep SNNs continue to suffer from over-parameterization during training and inference, a stark contrast to the brain’s ability to self-organize. Furthermore, existing sparse SNNs are challenged by maintaining optimal pruning levels due to a static pruning ratio, resulting in either under or over-pruning. In this paper, we propose a novel two-stage dynamic structure learning approach for deep SNNs, aimed at maintaining effective sparse training from scratch while optimizing compression efficiency. The first stage evaluates the compressibility of existing sparse subnetworks within SNNs using the PQ index, which facilitates an adaptive determination of the rewiring ratio for synaptic connections based on data compression insights. In the second stage, this rewiring ratio critically informs the dynamic synaptic connection rewiring process, including both pruning and regrowth. This approach significantly improves the exploration of sparse structures training in deep SNNs, adapting sparsity dynamically from the point view of compression efficiency. Our experiments demonstrate that this sparse training approach not only aligns with the performance of current deep SNNs models but also significantly improves the efficiency of compressing sparse SNNs. Crucially, it preserves the advantages of initiating training with sparse models and offers a promising solution for implementing Edge AI on neuromorphic hardware. © 2025, CC BY-NC-ND.

关键词：

Light-driven single-cell rotational adhesion frequency assay

学校读者我要写书评

暂无评论

eLight 2022年第1期2卷 154-164页

作者： Yaoran Liu Hongru Ding Jingang Li Xin Lou Mingcheng Yang Yuebing Zheng Department of Electrical and Computer Engineering The University of Texas at AustinAustinTX 78712USA Walker Department of Mechanical Engineering The University of Texas at AustinAustinTX 78712USA Materials Science&Engineering Program and Texas Materials Institute The University of Texas at AustinAustinTX 78712USA School of Physical Sciences University of Chinese Academy of SciencesBeijing 100049China Beijing National Laboratory for Condensed Matter Physics and Laboratory of Soft Matter Physics Institute of PhysicsChinese Academy of SciencesBeijing 100190China Songshan Lake Materials Laboratory Dongguan 523808GuangdongChina Department of Biomedical Engineering The University of Texas at AustinAustinTX 78712USA

The interaction between cell surface receptors and extracellular ligands is highly related to many physiological processes in living *** techniques have been developed to measure the ligand-receptor binding kinetics at the single-cell ***,few techniques can measure the physiologically relevant shear binding affinity over a single cell in the clinical ***,we develop a new optical technique,termed single-cell rotational adhesion frequency assay(scRAFA),that mimics in vivo cell adhesion to achieve label-free determination of both homogeneous and heterogeneous binding kinetics of targeted cells at the subcellular ***,the scRAFA is also applicable to analyze the binding affinities on a single cell in native human *** its superior performance and general applicability,scRAFA is expected to find applications in study of the spatial organization of cell surface receptors and diagnosis of infectious diseases.

关键词： diagnosis kinetics rotational