检索结果-内蒙古大学图书馆

2021 ieee/CVF conference on computer vision and pattern recognition, cvpr 2021

作者： Hong, Yicong Wu, Qi Qi, Yuankai Rodriguez-Opazo, Cristian Gould, Stephen The Australian National University Australian Centre for Robotic Vision Australia The University of Adelaide Australian Centre for Robotic Vision Australia

ISBN: (纸本)9781665445092

Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language (V&L) BERT. However, its application for the task of vision- and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously. © 2021 ieee

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Phase error analysis and compensation for motion in high-speed phase measurement profilometry

引用

OSA CONTINUUM 2021年第4期4卷 1191-1206页

作者： Li, Xuexing Zhang, Wenhui Wuxi Inst Technol Sch Mech Technol Wuxi 214121 Jiangsu Peoples R China Wuxi GNFIR Informat Technol Co Ltd Wuxi 214000 Jiangsu Peoples R China

High-speed three-dimensional (3D) measurement is increasingly important in many fields. Phase measurement profilometry (PMP) based on the binary defocusing technique has been applied to the high-speed 3D measurement scene for its higher measurement resolution and precision, and breaking the speed limitations of projector. However, because the PMP needs three phase-shifting (3-PS) patterns, motion error is inevitable to measuring dynamic objects. In this research, we construct a complete high-speed 3-PS PMP system, and re-derive two clearer motion error models than those in Weise's research [conference on computer vision and pattern recognition (cvpr) (ieee, 2007), pp. 1]. Then, we theoretically analyze the effects of the truncation error on the model accuracy, especially when the motion error is higher. To this end, a polynominal-based motion error model by fitting coefficient matrix of pre-simulation is proposed. Meanwhile, its corresponding error compensation method based on local domain estimation of the Nelder-Mead algorithm is developed. Finally, both simulations and quantitative and qualitative experiments verify the accuracy and effectiveness of the proposed method, as well as demonstrate the proposed method has improvements compared with the Weise's research. (c) 2021 Optical society of America under the terms of the OSA Open Access Publishing Agreement

关键词： High speed imaging Machine vision pattern recognition Phase measurement Phase unwrapping Precision metrology

来源：评论

学校读者我要写书评

暂无评论

Neurodata Lab's approach to the Challenge on computer vision for Physiological Measurement

Neurodata Lab's approach to the Challenge on Computer Vision...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Artemyev, Mikhail Churikova, Marina Grinenko, Mikhail Perepelkina, Olga Neurodata Lab LLC Miami FL 33137 USA Lomonosov Moscow State Univ Fac Biol Dept Higher Nervous Act Moscow Russia

ISBN: (纸本)9781728193601

This paper introduces the Neurodata Lab's approach presented at the 1st Challenge on Remote Physiological Signal Sensing (RePSS) organized within cvpr2020. The RePSS challenge was focused on measuring the average heart rate from color facial videos, which is one of the most fundamental problems in the field of computer vision. Our deep learning-based approach includes 3D spatio-temporal attention convolutional neural network for photoplethysmogram extraction and 1D convolutional neural network pre-trained on synthetic data for time series analysis. It provides state-of-the-art results outperforming those of other participants on a mixture of VIPL and OBF databases: MAE=6.94 (12.3% improvement compared to the top-2 result), RMSE=10.68 (24.6% improvement), Pearson R = 0.755 (28.2% improvement).

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Second Edition FRCSyn Challenge at cvpr 2024: Face recognition Challenge in the Era of Synthetic Data

Second Edition FRCSyn Challenge at CVPR 2024: Face Recogniti...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (cvprW)

作者： Ivan DeAndres-Tame Ruben Tolosana Pietro Melzi Ruben Vera-Rodriguez Minchul Kim Christian Rathgeb Xiaoming Liu Aythami Morales Julian Fierrez Javier Ortega-Garcia Zhizhou Zhong Yuge Huang Yuxi Mi Shouhong Ding Shuigeng Zhou Shuai He Lingzhi Fu Heng Cong Rongyu Zhang Zhihong Xiao Evgeny Smirnov Anton Pimenov Aleksei Grigorev Denis Timoshenko Kaleb Mesfin Asfaw Cheng Yaw Low Hao Liu Chuyi Wang Qing Zuo Zhixiang He Hatef Otroshi Shahreza Anjith George Alexander Unnervik Parsa Rahimi Sébastien Marcel Pedro C. Neto Marco Huber Jan Niklas Kolf Naser Damer Fadi Boutros Jaime S. Cardoso Ana F. Sequeira Andrea Atzori Gianni Fenu Mirko Marras Vitomir Štruc Jiang Yu Zhangjie Li Jichun Li Weisong Zhao Zhen Lei Xiangyu Zhu Xiao-Yu Zhang Bernardo Biesseck Pedro Vidal Luiz Coelho Roger Granada David Menotti Universidad Autonoma de Madrid Spain Michigan State University USA Hochschule Darmstadt Germany Fudan University China Tencent Youtu Lab China Interactive Entertainment Group of Netease Inc China ID R&D Inc. USA Korea Advanced Institute of Science & Technology Korea Institute for Basic Science Korea China Telecom AI China Idiap Research Institute Switzerland EPFL Switzerland Université de Lausanne Switzerland INESC TEC Portugal Universidade do Porto Portugal Fraunhofer IGD Germany University of Cagliari Italy University of Ljubljana Slovenia Samsung Electronics (China) R&D Centre China University of Science and Technology China IIE CAS China MAIS CASIA China Federal University of Paraná Brazil Federal Institute of Mato Grosso Brazil unico - idTech Brazil

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2 nd edition of the Face recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at cvpr 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1 st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2 nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2 nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

关键词： Training Data privacy Protocols Face recognition Transforms Manuals Machine learning

来源：评论

学校读者我要写书评

暂无评论

Understanding action recognition in still images

Understanding action recognition in still images

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Girish, Deeptha Singh, Vineeta Ralescu, Anca Univ Cincinnati Cincinnati OH 45220 USA

ISBN: (纸本)9781728193601

Action recognition in still images is closely related to various other computer vision tasks such as pose estimation, object recognition, image retrieval, video action recognition and frame tagging in videos. This problem is focused on recognizing a person's action or behavior using a single frame. Unlike action recognition in videos - a relatively very well established area of research where spatio-temporal features are used, these are not available for still images, making the problem more challenging. In the present work only actions that involve objects are considered. A complex action is broken down into components based on semantics. The importance of each of these components in action recognition is systematically studied.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 NonHomogeneous Dehazing Challenge Report

NTIRE 2021 NonHomogeneous Dehazing Challenge Report

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Ancuti, Codruta O. Ancuti, Cosmin Vasluianu, Florin-Alexandru Timofte, Radu Fu, Minghan Liu, Huan Yu, Yankun Chen, Jun Wang, Keyan Chang, Jerome Wang, Xiyao Liu, Jing Xu, Yi Zhang, Xinjian Zhao, Minyi Zhou, Shuigeng Chen, Tianyi Fu, Jiahui Jiang, Wentao Gao, Chen Liu, Si Wang, Yudong Guo, Jichang Li, Chongyi Yan, Qixin Zheng, Sida Zamir, Syed Waqas Arora, Aditya Dudhane, Akshay Khan, Salman Hayat, Munawar Khan, Fahad Shahbaz Shao, Ling Zhang, Haichuan Guo, Tiantong Monga, Vishal Yang, Wenjin Lin, Jin Luo, Xiaotong Huang, Guowen Chen, Shuxin Qu, Yanyun Xu, Kele Yang, Lehan Sun, Pengliang Niu, Xuetong Zheng, Junjun Ruan, Xiaotong Wang, Yunfeng Yang, Jiang Luo, Zhipeng Wang, Sai Xu, Zhenyu Cao, Xiaochun Luo, Jun Zheng, Zhuoran Ren, Wenqi Wang, Tao Chen, Yiqun Leng, Cong Li, Chenghua Cheng, Jian Sung, Chang-Sung Chen, Jun-Cheng Jo, Eunsung Sim, Jae-Young Geethu, M. M. Akhil, K. A. Sreeni, K. G. Jeena, R. S. Zacharias, Joseph Manu, Chippy M. Huang, Zexi Zhang, Baofeng Zhang, Yiwen Li, Jindong Chen, Mianjie Xiao, Quan Su, Qingchao Han, Lihua Huang, Yanting Prajapati, Kalpesh Chudasama, Vishal Patel, Heena Sarvaiya, Anjali Upla, Kishor Raja, Kiran Ramachandra, Raghavendra Busch, Christoph Jing, Hongyuan Huang, Zilong Fu, Yiran Wu, Haoqiang Zha, Quanxing Zhu, Zhiwei Lv, Hejun Univ Politehn Timisoara ETcTI Timisoara Romania UCL ICTEAM Louvain Belgium Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland McMaster Univ Hamilton ON Canada Xidian Univ Xian Peoples R China Natl Taiwan Univ Taipei Taiwan Univ Chinese Acad Sci Inst Automat Ctr Res Intelligent Syst & Engn Beijing Peoples R China Bilibili Inc Shanghai Peoples R China Fudan Univ Shanghai Peoples R China Beihang Univ Beijing Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Nanyang Technol Univ NTU Sch Comp Sci & Engn Singapore Singapore Incept Inst Artificial Intelligence IIAI Abu Dhabi U Arab Emirates Penn State Univ Sch Elect Engn & Comp Sci Informat Proc & Algorithms Lab iPAL University Pk PA 16802 USA Xiamen Univ Dept Comp Sci Xiamen Peoples R China Key Lab Parallel & Distributed Proc Changsha Peoples R China Alibaba Inc Shanghai Peoples R China DeepBlue Technol Shanghai Co Ltd Shanghai Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing Peoples R China CASIA Beijing Peoples R China CASIA AiRiA Beijing Peoples R China Natl Taiwan Univ Data Sci Degree Program Taipei Taiwan Ulsan Natl Inst Sci & Technol Ulsan South Korea Coll Engn Dept ECE CV Lab Trivandrum Kerala India AICTE Univ Kollam Kerala India South China Univ Techonol Sch Elect & Informat Engn Guangzhou Peoples R China Shenzhen Wave Kingdom Co Ltd Shenzhen Peoples R China Sardar Vallabhbhai Natl Inst Technol Surat India Beijing Union Univ Coll Robot Beijing Peoples R China

ISBN: (纸本)9781665448994

This work reviews the results of the NTIRE 2021 Challenge on Non-Homogeneous Dehazing. The proposed techniques and their results have been evaluated on a novel dataset that extends the NH-Haze datset. It consists of additional 35 pairs of real haze free and nonhomogeneous hazy images recorded outdoor. The nonhomogeneous haze has been introduced in the outdoor scenes by using a a professional setup that imitates the real conditions of haze scenes. 327 participants registered in the challenge and 23 teams competed in the final testing phase. The proposed solutions gauge the state-of-the-art in image dehazing.

关键词： computer vision Correlation conferences Architecture computer architecture pattern recognition Testing

来源：评论

学校读者我要写书评

暂无评论

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

Generalized Focal Loss V2: Learning Reliable Localization Qu...

引用

2021 ieee/CVF conference on computer vision and pattern recognition, cvpr 2021

作者： Li, Xiang Wang, Wenhai Hu, Xiaolin Li, Jun Tang, Jinhui Yang, Jian Nanjing University of Science and Technology Momenta Nanjing University Tsinghua University

Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-Maximum Suppression processing and improve detection performance. As a common practice, most existing methods predict LQE scores through vanilla convolutional features shared with object classification or bounding box regression. In this paper, we explore a completely novel and different perspective to perform LQE - based on the learned distributions of the four parameters of the bounding box. The bounding box distributions are inspired and introduced as “General Distribution” in GFLV1, which describes the uncertainty of the predicted bounding boxes well. Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality. Specifically, a bounding box distribution with a sharp peak usually corresponds to high localization quality, and vice versa. By leveraging the close correlation between distribution statistics and the real localization quality, we develop a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LQE based on GFLV1, thus producing GFLV2. To our best knowledge, it is the first attempt in object detection to use a highly relevant, statistical representation to facilitate LQE. Extensive experiments demonstrate the effectiveness of our method. Notably, GFLV2 (ResNet-101) achieves 46.2 AP at 14.6 FPS, surpassing the previous state-of-the-art ATSS baseline (43.6 AP at 14.6 FPS) by absolute 2.6 AP on COCO test-dev, without sacrificing the efficiency both in training and inference. © 2021 ieee

关键词： Location awareness Training computer vision Uncertainty Correlation Estimation Object detection

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Rarity in Human-object Interaction Detection

Diagnosing Rarity in Human-object Interaction Detection

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Kilickaya, Mert Smeulders, Arnold QUvA Deep Vis Lab Amsterdam Netherlands

ISBN: (纸本)9781728193601

Human-object interaction (HOI) detection is a core task in computer vision. The goal is to localize all human-object pairs and recognize their interactions. An interaction defined by a tuple leads to a long-tailed visual recognition challenge since many combinations are rarely represented. The performance of the proposed models is limited especially for the tail categories, but little has been done to understand the reason. To that end, in this paper, we propose to diagnose rarity in HOI detection. We propose a three-step strategy, namely Detection, Identification and recognition where we carefully analyse the limiting factors by studying state-of-the-art models. Our findings indicate that detection and identification steps are altered by the interaction signals like occlusion and relative location, as a result limiting the recognition accuracy.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded vision

Intelligent Scene Caching to Improve Accuracy for Energy-Con...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Simpson, Benjamin Lubana, Ekdeep Liu, Yuchen Dick, Robert Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781728193601

We describe an efficient method of improving the performance of vision algorithms operating on video streams by reducing the amount of data captured and transferred from image sensors to analysis servers in a data-aware manner. The key concept is to combine guided, highly heterogeneous sampling with an intelligent Scene Cache. This enables the system to adapt to spatial and temporal patterns in the scene, thus reducing redundant data capture and processing. A software prototype of our framework running on a general-purpose embedded processor enables superior object detection accuracy (by 56%) at similar energy consumption (slight improvement of 4%) compared to an H.264 hardware accelerator.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

As Seen on TV: Automatic Basketball Video Production using Gaussian-based Actionness and Game States recognition

As Seen on TV: Automatic Basketball Video Production using G...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Quiroga, Julian Carrillo, Henry Maldonado, Edisson Ruiz, John Zapata, Luis M. Genius Sports Comp Vis Medellin Colombia

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193601

Automatic video production of sports aims at producing an aesthetic broadcast of sporting events. We present a new video system able to automatically produce a smooth and pleasant broadcast of Basketball games using a single fixed 4K camera. The system automatically detects and localizes players, ball and referees, to recognize main action coordinates and game states yielding to a professional cameraman-like production of the basketball event. We also release a fully annotated dataset consisting of single 4K camera and twelve-camera videos of basketball games.

关键词： Cameras Games Production Streaming media Robot vision systems Computational modeling

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：