检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Weihua Chen Lijun Cao Xiaotang Chen Kaiqi Huang Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781479957521

The traditional multi-camera object tracking contains two steps: single camera object tracking (SCT) and inter-camera object tracking (ICT). The ICT performance strongly relies on the great results of SCT. In practice, most of current SCT methods are unperfect and products much more fragments. In this paper, a novel solution using a global tracklet association is proposed, which can provide a good ICT performance when the SCT results are not perfect. The proposed solution is also available in non-overlapping views through a new tracklet representation and experiments shows the effectiveness of the proposed novel solution in real scene.

关键词： Multi-camera object tracking Global tracklet association PMCSHR

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparative Analysis of Africans with Asians Using DCNN Facial Biometric Models 16th

An Empirical Comparative Analysis of Africans with Asians ...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Muhammad, Jawad Wang, Yunlong Wang, Leyuan Zhang, Kunbo Sun, Zhenan School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031202322

Recently, the problem of racial bias in facial biometric systems has generated considerable attention from the media and biometric community. Many investigative studies have been published on estimating the bias between Caucasians and Asians, Caucasians and Africans, and other racial comparisons. These studies have reported inferior performances of both Asians and Africans when compared to other races. However, very few studies have highlighted the comparative differences in performance as a function of race between Africans and Asians. More so, those previous studies were mainly concentrated on a single aspect of facial biometrics and were usually conducted with images potentially captured with multiple camera sensors, thereby compounding their findings. This paper presents a comparative racial bias study of Asians with Africans on various facial biometric tasks. The images used were captured with the same camera sensor and under controlled conditions. We examine the performances of many DCNN-based models on face detection, facial landmark detection, quality assessment, verification, and identification. The results suggested higher performance on the Asians compared to the Africans by most algorithms under the same imaging and testing conditions. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Biologically inspired visual computing:the state of the art

引用

Frontiers of Computer Science 2021年第1期15卷 1-15页

作者： Wangli HAO Ian Max ANDOLINA Wei WANG Zhaoxiang ZHANG Research Center for Research on Intelligent Perception and Computing Beijing 100190China National Laboratory of Pattern Recognition CASIABeijing 100190China CAS Center for Excellence in Brain Science and Intelligence Technology CASBeijing 100190China University of Chinese Academy of Sciences Beijing 100190China State Key Laboratory of Neuroscience Shanghai 200031China Institute of Neuroscience Chinese Academy of SciencesShanghai 200031China

Visual information is highly advantageous for the evolutionary success of almost all *** information is likewise critical for many computing tasks,and visual computing has achieved tremendous successes in numerous applications over the last 60 years or *** that time,the development of visual computing has moved forwards with inspiration from biological mechanisms many *** particular,deep neural networks were inspired by the hierarchical processing mechanisms that exist in the visual cortex of primate brains(including ours),and have achieved huge breakthroughs in many domainspecific visual *** order to better understand biologically inspired visual computing,we will present a survey of the current work,and hope to offer some new avenues for rethinking visual computing and designing novel neural network architectures.

关键词： brain-inspired vision neural models intelligence novel neural networks

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution 15

Bidirectional Recurrent Convolutional Networks for Multi-Fra...

引用

Annual Conference on Neural Information Processing Systems

作者： Yan Huang Wei Wang Liang Wang Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Center for Excellence in Brain Science and Intelligence Technology Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781510825024

Super resolving a low-resolution video is usually handled by either single-image super-resolution (SR) or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video super-resolution. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, which often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term contextual information of temporal sequences well, we propose a bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used recurrent full connections are replaced with weight-sharing convolutional connections and 2) conditional convolutional connections from previous input layers to the current hidden layer are added for enhancing visual-temporal dependency modelling. With the powerful temporal dependency modelling, our model can super resolve videos with complex motions and achieve state-of-the-art performance. Due to the cheap convolution operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame methods.

关键词： multiframe Videotapes Input Layer super-resolution VIDEO FRAMES SAVANNAH RIVER OPERATIONS OFFICE Strontium Optic Flow complexity classes

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Graph Contrastive Learning 35

An Empirical Study of Graph Contrastive Learning

引用

35th Conference on Neural Information Processing Systems - Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021

作者： Zhu, Yanqiao Xu, Yichen Liu, Qiang Wu, Shu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer Science Beijing University of Posts and Telecommunications China

Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining strategies. Then, to understand the interplay of different GCL components, we conduct comprehensive, controlled experiments over benchmark tasks on datasets across various domains. Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentations that produce sparse graph views bring promising performance improvements;contrasting modes should be aligned with the granularities of end tasks. In addition, to foster future research and ease the implementation of GCL algorithms, we develop an easy-to-use library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research. © 2021 Neural information processing systems foundation. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CoCo DistillNet: A Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation

CoCo DistillNet: A Cross-layer Correlation Distillation Netw...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zou, Wenxuan Qi, Xingqun Wu, Zhuojie Wang, Zijian Sun, Muyi Shan, Caifeng Beijing University of Posts and Telecommunications School of Automation Beijing China Center for Research on Intelligent Perception and Computing NLPR CASIA Beijing China Shandong University of Science and Technology Qingdao266590 China Beijing100190 China

ISBN: (纸本)9781665401265

In recent years, deep convolutional neural networks have made significant advances in pathology image segmentation. However, pathology image segmentation encounters with a dilemma in which the higher-performance networks generally require more computational resources and storage. This phenomenon limits the employment of high-accuracy networks in real scenes due to the inherent high-resolution of pathological images. To tackle this problem, we propose CoCo DistillNet, a novel Cross-layer Correlation (CoCo) knowledge distillation network for pathological gastric cancer segmentation. Knowledge distillation, a general technique which aims at improving the performance of a compact network through knowledge transfer from a cumbersome network. Concretely, our CoCo DistillNet models the correlations of channel-mixed spatial similarity between different layers and then transfers this knowledge from a pre-trained cumbersome teacher network to a non-trained compact student network. In addition, we also utilize the adversarial learning strategy to further prompt the distilling procedure which is called Adversarial Distillation (AD). Furthermore, to stabilize our training procedure, we make the use of the unsupervised Paraphraser Module (PM) to boost the knowledge paraphrase in the teacher network. As a result, extensive experiments conducted on the Gastric Cancer Segmentation Dataset demonstrate the prominent ability of CoCo DistillNet which achieves state-of-the-art performance. © 2021 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Review of Inference Time Prediction Approaches of DNN: Emphasis on Service robots with cloud-edge-device architecture

Review of Inference Time Prediction Approaches of DNN: Empha...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Xiang, Tian Meng, Qiwei Zhang, Ji Zhang, Beibei Song, Wei Xie, Anhuan Gu, Jason Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Research Center for Intelligent Robotics Hangzhou311100 China The Chinese University of Hong Kong T Stone Robotics Institute Department of Mechanical and Automation Engineering Hong Kong Research Institute of Intelligent Computing Zhejiang Laboratory Research Center for Intelligent Computing Software Hangzhou311100 China Dalhousie University Electrical and Computer Engineering Halifax Canada

ISBN: (纸本)9798350325706

In recent years, the global robot market has witnessed substantial growth, particularly in the domain of service robots. Despite their expanding presence, service robots encounter limitations when operating autonomously in unstructured environments, primarily due to their constrained computational capacities. As a solution, the fusion of cloud and edge computing resources becomes imperative to expedite task inference and enhance scenario perception capabilities. The integration of cloud-edge-device models holds significant promise in bolstering the operational efficiency of robots. This entails the dynamic partitioning of intricate robotic tasks, executed collaboratively across cloud, edge, and device resources. In this landscape, deep neural network (DNN) models play a pivotal role in facilitating a wide array of robotic tasks. The inference time for each layer of a DNN model in actual deployment, emerges as a critical determinant in the model's partitioning strategy. It also serves as an important metric influencing the model's suitability for a specific hardware platform. This article presents an overview of recent advancements in predicting inference and training time of DNN models, summarizes the related methods, and finally discusses the challenges in this field and the research that can be studied in the future. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coupled feature selection for cross-sensor iris recognition

Coupled feature selection for cross-sensor iris recognition

引用

IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS)

作者： Lihu Xiao Zhenan Sun Ran He Tieniu Tan Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences Beijing P.R. China

It is necessary to match heterogeneous iris images captured by different types of iris sensors with an increasing demand of interoperable identity management systems. The significant differences among multiple types of iris sensors such as optical lens and illumination wavelength determine the cross-sensor variations of iris texture patterns. Therefore it is a challenging problem to select the common feature set which is effective for all types of iris sensors. This paper proposes a novel optimization model of coupled feature selection for cross-sensor iris recognition. The objective function of our model includes two parts: the first part aims to minimize the misclassification errors; the second part is designed to achieve sparsity in coupled feature spaces based on l 2,1 -norm regularization. In the training stage, the proposed feature selection model can be formulated as a half-quadratic optimization problem, where an iterative algorithm is developed to obtain the solution. Experimental results on the Notre Dame Cross Sensor Iris Database and CASIA cross sensor iris database show that features selected by the proposed method perform better than those selected by conventional single-space feature selection methods such as Boosting and h regularization methods.

关键词： Iris recognition Sensors Image sensors Databases Iris Minimization Optimization

来源：评论

学校读者我要写书评

暂无评论

Inconsistency-Aware Wavelet Dual-Branch Network for Face Forgery Detection

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity Science 2021年第3期3卷 308-319页

作者： Jia, Gengyun Zheng, Meisong Hu, Chuanrui Ma, Xin Xu, Yuting Liu, Luoqi Deng, Yafeng He, Ran School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China 360 Ai Institute Beijing Qihu Keji Company Ltd. Beijing China 360 Ai Institute Beijing Qihu Keji Company Ltd. Beijing100020 China National Laboratory of Pattern Recognition Center for Research on Intelligent Perception and Computing Cas Center for Excellence in Brain Science and Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China

Current face forgery techniques can generate high-fidelity fake faces with extremely low labor and time costs. As a result, face forgery detection becomes an important research topic to prevent technology abuse. In this paper, we present an inconsistency-aware wavelet dual-branch network for face forgery detection. This model is mainly based on two kinds of forgery clues called inter-image and intra-image inconsistencies. To fully utilize them, we firstly enhance the forgery features by using additional inputs based on stationary wavelet decomposition (SWD). Then, considering the different properties of the two inconsistencies, we design a dual-branch network that predicts image-level and pixel-level forgery labels respectively. The segmentation branch aims to recognize real and fake local regions, which is crucial for discovering intra-image inconsistency. The classification branch learns to discriminate the real and fake images globally, thus can extract inter-image inconsistency. Finally, bilinear pooling is employed to fuse the features from the two branches. We find that the bilinear pooling is a kind of spatial attentive pooling. It effectively utilizes the rich spatial features learned by the segmentation branch. Experimental results show that the proposed method surpasses the state-of-the-art face forgery detection methods. © 2019 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Traversability Analysis for Unmanned Ground Vehicles Based on Multi-modal Information Fusion

Traversability Analysis for Unmanned Ground Vehicles Based o...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Wen, Mingxing Guo, Jiajie Zhou, Yichen Zhang, Jun Yue, Yufeng Wang, Danwei China Singapore International Joint Research Institute Intelligent Perception Innovation Research Center China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Beijing Institute of Technology School of Automation Beijing100081 China

ISBN: (纸本)9798350325706

How to efficiently and safely navigate unmanned ground vehicles in unstructured off-road environments still faces several challenges, such as various terrains and highly dynamic scenarios. Traversability analysis presents tremendous potential in addressing these problems by perceiving surroundings and building travesability maps. In this paper, a novel traversability analysis algorithm based on multi-modal information fusion has been proposed. This algorithm comprehensively leverages data from both LiDAR and camera to understand the characteristics of the environment. Point clouds are utilized to extract geometric features such as flat surfaces, slopes and depressions, and semantic segmentation of images enables the identification of various terrains as well as dynamic objects. These two types of information will be effectively fused and integrated to generate a traversability map on the fly, which is dynamically insensitive. To verify the performance and effectiveness, the algorithm has been deployed on an Unmanned Ground Vehicle(UGV) where MMDeploy Toolbox has been used to accelerate the inference speed of the segmentation model and maintain the input stream frequency of mapping at around 10 Hz. Extensive experiments have been conducted within campus and the algorithm demonstrates robustness in such environment with diverse terrains and dynamic objects. © 2023 IEEE.

关键词：

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：