检索结果-内蒙古大学图书馆

Scalable receptive field GAN: An end-to-end adversarial learning framework for crowd counting 1

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Gao, Yukang Yang, Hua Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Crowd counting is challenging for unrestricted open outdoor and diverse scenes. To address large variety of perspective, density distribution and clutter problems, a novel end-to-end deep generative adversarial framework with scalable receptive field (SRFGAN) is proposed for obtaining high quality density estimation in this paper. Specifically, our generator adopts an encoder-decoder network with residual blocks to achieve multi-scale features due to scalable receptive fields which adapts to different scale crowd distribution. We also explore a spatial global pooling layer to acquire image-level prior representation which helps to tackle severe perspective distortion and background clutter. Besides, feature matching loss and adversarial loss are combined via a joint training scheme, which helps to improve the quality of generated density map. Experiment results on ShanghaiTech and UCF CC 50 datasets illustrate the superior effectiveness. © Springer Nature Switzerland AG 2019.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Crowd Behavior Analysis System Based on B/S Software Architecture 16th

Design and Optimization of Crowd Behavior Analysis System Ba...

引用

16th International Forum on Digital TV and Wireless Multimedia communication, IFTC 2019

作者： He, Yuanhang Guo, Jing Ji, Xiang Yang, Hua Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China China Academic of Electronics and Information Technology Beijing China

ISBN: (纸本)9789811533402

With the development of society and economy, the importance of crowd behavior analysis is increasing. However, the system often requires a large amount of computing resources, which is often difficult to meet for personal computers in traditional client/server architecture (C/S architecture). So based on the existing local analysis system [5], we construct a crowd behavior analysis system based on browser/server architecture (B/S architecture). Then we optimize many aspects of this B/S system to improve its communication capability and stability under high load. Finally, the acceleration work of the CGAN-based crowd counting module is carried out. The generator of CGAN (Conditional Generative Adversarial network) was optimized such as residual layer pruning, upsampling optimization, and instance normalization layer removing, and then deployed and INT8 quantized in TensorRT. After these optimizations, the inferring speed on the NVIDIA platform is increased to 541.6% of the original network with almost no loss of inference accuracy. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Jinhai Yang, Hua Shanghai Jiao Tong University Institution of Image Communication and Network Engineering China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

ISBN: (纸本)9781728163277

Few-shot learning aims for rapid adaptation with few samples. Recently, cross-granularity few-shot learning has emerged as a promising research area, where models observe coarse labels but target fine-grained recognition among novel classes. As coarse supervision tends to eliminate feature discrimination among underlying sub-classes, existing methods commonly utilize self-supervision as a complement to explore intra-class variation. However, current methods suffer from an intrinsic conflict between contrastive learning and coarse supervision. In this paper, we locate the root cause of the intrinsic conflict. Then, we resolve it by exploiting the similarity among augmented views while ignoring the unreasonable constraint between negative pairs. Besides, we decouple contrastive learning and coarse supervision into parallel branches to better regularize the latent space. Albeit simple, our approach consistently outperforms state-of-the-art methods across different benchmarks. © 2023 IEEE.

关键词： cross-granularity transfer Few-shot learning generalization image classification

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Top-Down Single-Task Action Recognition in Still images 16th

Attention-Based Top-Down Single-Task Action Recognition in S...

引用

16th International Forum on Digital TV and Wireless Multimedia communication, IFTC 2019

作者： Yang, Jinhai Zhou, Xiao Yang, Hua Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Suzhou Keensense Technology Co. Ltd. Suzhou China

ISBN: (纸本)9789811533402

Human action recognition via deep learning methods in still images has been an active research topic in computer vision recently. Different from the traditional action recognition based on videos or image sequences, a single image contains no temporal information or motion features for action characterization. In this study, we utilize a top-down action recognition strategy to analyze person instances in a scene respectively, on the task of detecting determine persons playing a cellphone. A YOLOv3 detector is applied to predict the human bounding boxes, and the HRNet (High Resolution network) is used to regress the attention map centered on the area of playing a cellphone, taking the region of given human bounding box as the input. Experimental results on a custom dataset show that HRNet can reliably represent a person image to a heatmap where the region of interest (ROI) is highlighted. The accuracy of the proposed framework exceeds the performance of all the evaluated naive classification models, i.e., Densenet, inception_v3 and shufflenet_v2. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Series-Parallel Compensated IPT System with Load-Independent Voltage Gain and Efficiency

A Series-Parallel Compensated IPT System with Load-Independe...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Chang Gao Laipeng Zhang Bo Li Lianghui Ding Feng Yang Liang Qian Institution of Wireless Communication Technology Shanghai Jiao Tong University Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781509035298

In this paper, by first analyzing the circuit model of series-parallel compensated inductive power transfer (IPT) system, the relation among voltage gain, transfer efficiency, operation frequency and load resistance is obtained. According to the analysis, a novel design of series-parallel compensated IPT system realizing optimized transfer efficiency and voltage gain regardless of load resistance is then proposed. Simulation and experiment verification are carried out with various load resistances. An almost load-independent voltage gain and efficiency up to 96.8% are achieved when the air gap between coupled coils is 17.91mm.

关键词： Coils Capacitors Resistance Integrated circuit modeling Load modeling Couplings Analytical models

来源：评论

学校读者我要写书评

暂无评论

引用

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

作者： Jinhai Yang Hua Yang Institution of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

关键词： Adaptation models Target recognition Semantics Signal processing Performance gain Benchmark testing Acoustics

来源：评论

学校读者我要写书评

暂无评论

Crowd Counting Via Multi-Level Regression With Latent Gaussian Maps

Crowd Counting Via Multi-Level Regression With Latent Gaussi...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Yukang Gao Hua Yang Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai key lab of digital media processing and transmission Shanghai China

Crowd counting still confronts two primary challenges: limited ability to deal with cross density levels caused by fixed density maps and lack of fine-grained or coarse-grained guidance for density estimation. In this paper, a novel end-to-end crowd counting framework via multi-level regression with latent Gaussian maps is proposed, which is consisted of GaussianNet, EstimateNet and Discriminator. GaussianNet is composed of masked Gaussian convolutional blocks and vanillia convolutional layers, to generate latent Gaussian maps adaptively for various density levels. The latent Gaussian maps are then treated as the ground truth density maps for EstimateNet, which outputs density estimations and follows the principle of adversarial learning with Discriminator. Moreover, multi-level losses are combined for density map regression guidance. Extensive experiments on the major public datasets outperform state-of-the-art ones, illustrating the superior validity of the proposed framework.

关键词： Training Convolution Conferences Estimation Acoustics Bayes methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Attentive semantic exploring for manipulated face detection

arXiv

引用

arXiv 2020年

作者： Chen, Zehao Yang, Hua Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Lab of Degital Media Processing and Transmission Shanghai China

Face manipulation methods develop rapidly in recent years, whose potential risk to society accounts for the emerging of researches on detection methods. However, due to the diversity of manipulation methods and the high quality of fake images, detection methods suffer from a lack of generalization ability. To solve the problem, we find that segmenting images into semantic fragments could be effective, as discriminative defects and distortions are closely related to such fragments. Besides, to highlight discriminative regions in fragments and to measure contribution to the final prediction of each fragment is efficient for the improvement of generalization ability. Therefore, we propose a novel manipulated face detection method based on Multilevel Facial Semantic Segmentation and Cascade Attention Mechanism. To evaluate our method, we reconstruct two datasets: GGFI and FFMI, and also collect two open-source datasets. Experiments on four datasets verify the advantages of our approach against other state-of-the-arts, especially its generalization ability. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Efficient MedSAMs: Segment Anything in Medical images on Laptop

arXiv

引用

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

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：