检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zong, Zhuofan Li, Kunchang Song, Guanglu Wang, Yali Qiao, Yu Leng, Biao Liu, Yu School of Computer Science and Engineering Beihang University China SenseTime Research China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Shanghai AI Laboratory China

vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7× with negligible accuracy drop, and even speed up ViTs by 3.6× while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://***/Sense-X/SiT. © 2021, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection

arXiv

引用

arXiv 2022年

作者： Liu, Yi Zhang, Xuan Li, Ying Liang, Guixin Jiang, Yabing Qiu, Lixia Tang, Haiping Xie, Fei Yao, Wei Dai, Yi Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shenzhen Bwell Technology Co. Ltd China Shenzhen Longhua Drainage Co. Ltd China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Video understanding is an important problem in computer vision. Currently, the well-studied task in this research is human action recognition, where the clips are manually trimmed from the long videos, and a single class of human action is assumed for each clip. However, we may face more complicated scenarios in the industrial applications. For example, in the real-world urban pipe system, anomaly defects are fine-grained, multi-labeled, domain-relevant. To recognize them correctly, we need to understand the detailed video content. For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis. In particular, we introduce two high-quality video benchmarks, namely QV-Pipe and CCTV-Pipe, for anomaly inspection in the real-world urban pipe systems. Based on these new datasets, we will host two competitions including (1) Video Defect Classification on QV-Pipe and (2) Temporal Defect Localization on CCTV-Pipe. In this report, we describe the details of these benchmarks, the problem definitions of competition tracks, the evaluation metric, and the result summary. We expect that, this competition would bring new opportunities and challenges for video understanding in smart city and beyond. The details of our VideoPipe challenge can be found in https://***. Copyright © 2022, The Authors. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

UniFormer: Unifying Convolution and Self-attention for Visual recognition

arXiv

引用

arXiv 2022年

作者： Li, Kunchang Wang, Yali Zhang, Junhao Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China National University of Singapore Singapore Shanghai Artificial Intelligence Laboratory China SenseTime Research China The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification task. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4× higher throughput than the recent lightweight models. Code is av

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

Detach and Enhance: Learning Disentangled Cross-modal Latent...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhenning Yu Xin Liu Yiu-Ming Cheung Minghang Zhu Xing Xu Nannan Wang Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Dept. of Comput. Sci. and Institute of Research and Continuing Education HK Baptist University Hong Kong SAR China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China State Key Lab. of Integrated Services Networks & School of Telecommun. Eng. Xidian University Xi’an China

Many researches in cognitive science have shown that humans often perform face-voice association for various perception tasks, and some recent data mining works have been designed in emulating such ability intelligently. Nevertheless, most methods often suffer from the degraded performance when there exist semantically irrelevant interference factors across different modalities. To alleviate this concern, this paper presents an efficient Disentangled Cross-modal Latent Representation (DCLR) method to adaptively detach the discriminative feature attributes and enhance the face-voice association. To be specific, the proposed DCLR framework consists of two-stage cross-modal disentangling process. First, the former stage employs the supervised contrastive learning to push the representations of face-voice data from the same person closer while pulling those representations of different person away. Then, the latter stage freezes all the parameters of the former stage, and further innovates a multi-layer orthogonal decoupling scheme to learn the disentangled latent representations, while filtering out the modality-dependent irrelevant factors. Besides, the cross-modal reconstruction loss is further utilized to narrow down the semantic gap between heterogeneous feature expressions. Through the joint exploitation of the above, the proposed framework can well associate the face-voice data to benefit various kinds of cross-modal perception tasks. Extensive experiments verify the superiorities of the proposed face-voice association framework and show its competitive performances.

关键词： Representation learning Filtering Semantics Interference Data models Cognitive science Data mining

来源：评论

学校读者我要写书评

暂无评论

Road Segmentation via Iterative Deep Analysis

Road Segmentation via Iterative Deep Analysis

引用

IEEE International Conference on Robotics and Biomimetics

作者： Xiang Chen Yu Qiao Student at Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Address: 1068 Xueyuan Avenue Shenzhen University Town Shenzhen P.R.China Researcher at Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Address: 1068 Xueyuan Avenue Shenzhen University Town Shenzhen P.R.China

ISBN: (纸本)9781467396769

Nowadays, people are increasingly concerned about the safety of traffic systems. Road segmentation and recognition is a fundamental problem in perceiving traffic environments and serve as the basis for self-driving cars. In this paper, inspired by an iterative deep analysis thinking, we propose a novel method which is able to learning powerful features step by step, and solve the optimal precision by balancing local and global information to conduct pixel-level classification for road segmentation. Firstly, we introduce an iterative deep analysis thinking which shows that how to design a strong and robustness deep model from failure experience. Secondly, we choose a powerful global features learning network as basis to create a novel framework for our task. Meanwhile, we employ the patch and multi-scale pyramid as input to enhance local features learning. We conduct experiments on three datasets from KITTI vision Benchmark, namely UU, UM, UMM. The experimental results demonstrate that our proposed method obtains comparable performance with state-of-the-art methods on these datasets.

关键词： recognition fundamental datasets

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

NTIRE 2023 Image Shadow Removal Challenge Report

引用

2023 IEEE/CVF Conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to Intrusion detection based on improved density peak clustering for imbalanced data on sensor-cloud systems Journal of Systems Architecture volume 118 (2021) 102212

引用

Journal of Systems Architecture 2021年 119卷

作者： Ming Yan Yewang Chen Xiaoliang Hu Dongdong Cheng Yi Chen Jixiang Du The College of Computer Science and Technology Huaqiao University Xiamen China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University Beijing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing China

来源：评论

学校读者我要写书评

暂无评论

Clustering-based Discriminative Locality Alignment for Face Gender recognition

Clustering-based Discriminative Locality Alignment for Face ...

引用

IEEE/RSJ International Conference on Intelligent Robotics and Systems

作者： Duo Chen Jun Cheng Dacheng Tao College of Communication Engineering Chongqing University Chongqing 400044 China. He is also with the Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China. He is also with the Chinese University of Hong Kong and Guangdong Provincial Key Laboratory of Robotics and Intelligent System. Center for Quantum Computation and Intelligent System Faculty of Engineering and Information Technology University of Technology Sydney New South Wales 2007 Australia.

ISBN: (数字)9781467317368

ISBN: (纸本)9781467317375

To facilitate human-robot interactions, human gender information is very important. Motivated by the success of manifold learning for visual recognition, we present a novel clustering-based discriminative locality alignment (CDLA) algorithm to discover the low-dimensional intrinsic submanifold from the embedding high-dimensional ambient space for improving the face gender recognition performance. In particular, CDLA exploits the global geometry through k-means clustering, extracts the discriminative information through margin maximization and explores the local geometry through intra cluster sample concentration. These three properties uniquely characterize CDLA for face gender recognition. The experimental results obtained from the FERET data sets suggest the superiority of the proposed method in terms of recognition speed and accuracy by comparing with several representative methods.

关键词： FERET CDLA comparing recognition (Psychology) Gender Global geometry Compare Face Face

来源：评论

学校读者我要写书评

暂无评论

ChaLearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition

arXiv

引用

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on pattern recognition (ICPR) 2016 and International Conference on computer vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results

arXiv

引用

arXiv 2021年

作者： Pan, Liang Wu, Tong Cai, Zhongang Liu, Ziwei Yu, Xumin Rao, Yongming Lu, Jiwen Zhou, Jie Xu, Mingye Luo, Xiaoyuan Fu, Kexue Gao, Peng Wang, Manning Wang, Yali Qiao, Yu Zhou, Junsheng Wen, Xin Xiang, Peng Liu, Yu-Shen Han, Zhizhong Yan, Yuanjie An, Junyi Zhu, Lifa Lin, Changwei Liu, Dongrui Li, Xin Gómez-Fernández, Francisco Wang, Qinlong Yang, Yang S-Lab Nanyang Technological University Singapore SenseTime-CUHK Joint Lab The Chinese University of Hong Kong Hong Kong Sensetime Research Shanghai AI Laboratory China Department of Automation Tsinghua University China University of Chinese Academy of Sciences China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Digital Medical Research Center School of Basic Medical Science Fudan University China School of Software BNRist Tsinghua University China *** Wayne State University State Key Laboratory for Novel Software Technology Nanjing University China DeepGlint Shanghai Jiao Tong University China Sichuan University China Xi'an Jiaotong University China

As real-scanned point clouds are mostly partial due to occlusions and viewpoints, reconstructing complete 3D shapes based on incomplete observations becomes a fundamental problem for computer vision. With a single incomplete point cloud, it becomes the partial point cloud completion problem. Given multiple different observations, 3D reconstruction can be addressed by performing partial-to-partial point cloud registration. Recently, a large-scale Multi-View Partial (MVP) point cloud dataset has been released, which consists of over 100,000 high-quality virtual-scanned partial point clouds. Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration. In total, 128 participants registered for the competition, and 31 teams made valid submissions. The top-ranked solutions will be analyzed, and then we will discuss future research directions. Copyright © 2021, The Authors. All rights reserved.

关键词： Surface measurement

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：