检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Luyao Chen, Zhiqiang Jiang, Longsheng Liu, Xiang Xu, Linlu Zhang, Bo Zou, Xiaolong Gao, Jinying Zhu, Yu Gong, Xizi Yu, Shan Song, Sen Chen, Liangyi Fang, Fang Wu, Si Liu, Jia AI of Brain and Cognitive Sciences Research Group Beijing Academy of Artificial Intelligence Beijing100084 China School of Psychology and Cognitive Sciences Peking University Beijing100871 China Brainnetome Center National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Tsinghua Laboratory of Brain and Intelligence Tsinghua University Beijing100084 China State Key Laboratory of Membrane Biology Institute of Molecular Medicine Peking-Tsinghua Center for Life Sciences College of Future Technology Peking University Beijing100871 China

Nowadays, we have witnessed the great success of ai in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation. Despite these powerful applications, there are still many tasks in our daily life that are rather simple to humans but pose great challenges to ai. These include image and language understanding, few-shot learning, abstract concepts, and low-energy cost computing. Thus, learning from the brain is still a promising way that can shed light on the development of next-generation ai. The brain is arguably the only known intelligent machine in the universe, which is the product of evolution for animals surviving in the natural environment. At the behavior level, psychology and cognitive sciences have demonstrated that human and animal brains can execute very intelligent high-level cognitive functions. At the structure level, cognitive and computational neurosciences have unveiled that the brain has extremely complicated but elegant network forms to support its functions. Over years, people are gathering knowledge about the structure and functions of the brain, and this process is accelerating recently along with the initiation of giant brain projects worldwide. Here, we argue that the general principles of brain functions are the most valuable things to inspire the development of ai. These general principles are the standard rules of the brain extracting, representing, manipulating, and retrieving information, and here we call them the first principles of the brain. This paper collects six such first principles. They are attractor network, criticality, random network, sparse coding, relational memory, and perceptual learning. On each topic, we review its biological background, fundamental property, potential application to ai, and future development. © 2023, CC BY.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Multiple domain experts collaborative learning: Multi-source domain generalization for person re-identification

arXiv

引用

arXiv 2021年

作者： Yu, Shijie Zhu, Feng Chen, Dapeng Zhao, Rui Chen, Haobin Zhu, Jinguo Tang, Shixiang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China SenseTime Group Limited Shanghai AI Lab Shanghai China Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China

Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when unseen testing domains exhibit different characteristics from the source training ones, known as the domain generalization problem. Given multiple source training domains, previous Domain Generalizable ReID (DG-ReID) methods usually learn all domains together using a shared network, which can't learn sufficient knowledge from each domain. In this paper, we propose a novel Multiple Domain Experts Collaborative Learning (MECL) framework for better exploiting all training domains, which benefits from the proposed Domain-Domain Collaborative Learning (DDCL) and Universal-Domain Collaborative Learning (UDCL). DDCL utilizes domain-specific experts for fully exploiting each domain, and prevents experts from over-fitting the corresponding domain using a meta-learning strategy. In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts. Note, only the universal expert will be used for inference. Extensive experiments on DG-ReID benchmarks demonstrate the effectiveness of DDCL and UDCL, and show that the whole MECL framework significantly outperforms state-of-the-arts. Experimental results on DG-classification benchmarks also reveal the great potential of applying MECL to other DG tasks. Code will be released. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

arXiv

引用

arXiv 2021年

作者： Sun, Hao Xu, Guangxuan Deng, Jiawen Cheng, Jiale Zheng, Chujie Zhou, Hao Peng, Nanyun Zhu, Xiaoyan Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China University of California Los Angeles United States Pattern Recognition Center WeChat AI Tencent Inc China

Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works. To spur research in this direction, we compile DIASAFETY, a dataset with rich context-sensitive unsafe examples. Experiments show that existing safety guarding tools fail severely on our dataset. As a remedy, we train a dialogue safety classifier to provide a strong baseline for context-sensitive dialogue unsafety detection. With our classifier, we perform safety evaluations on popular conversational models and show that existing dialogue systems still exhibit concerning context-sensitive safety problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Enhanced Boundary Learning for Glass-like Object Segmentation

arXiv

引用

arXiv 2021年

作者： He, Hao Li, Xiangtai Cheng, Guangliang Shi, Jianping Tong, Yunhai Meng, Gaofeng Prinet, Véronique Weng, Lubin National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Peking University China SenseTime Group Research Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation CAS 6 Shanghai AI Lab China

Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module that outputs finer boundary cues. We then introduce an edge-aware point-based graph convolution network module to model the global shape along the boundary. We use these two modules to design a decoder that generates accurate and clean segmentation results, especially on the object contours. Both modules are lightweight and effective: they can be embedded into various segmentation models. In extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, our approach establishes new state-of-the-art results. We also illustrate the strong generalization properties of our method on three generic segmentation datasets, including Cityscapes, BDD, and COCO Stuff. Code and models is available at https://***/hehao13/EBLNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Glass

来源：评论

学校读者我要写书评

暂无评论

Enhanced Boundary Learning for Glass-like Object Segmentation

Enhanced Boundary Learning for Glass-like Object Segmentatio...

引用

International Conference on Computer Vision (ICCV)

作者： Hao He Xiangtai Li Guangliang Cheng Jianping Shi Yunhai Tong Gaofeng Meng Véronique Prinet LuBin Weng National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Key Laboratory of Machine Perception (MOE) Peking University SenseTime Group Research Shanghai AI Lab Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation CAS

ISBN: (纸本)9781665428132

关键词： Shape Convolution Navigation Semantics Object segmentation Predictive models Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Improving multi-turn dialogue modelling with utterance rewriter

arXiv

引用

arXiv 2019年

作者： Su, Hui Shen, Xiaoyu Zhang, Rongzhi Sun, Fei Hu, Pengwei Niu, Cheng Zhou, Jie Pattern Recognition Center Wechat AI Tencent Inc China Saarland Informatics Campus Institute of Software University of Chinese Academy of Science Alibaba Group IBM Research China

Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains. Copyright © 2019, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Point Tracking in Surgery–The 2024 Surgical Tattoos in Infrared (STIR) Challenge

arXiv

引用

arXiv 2025年

作者： Schmidt, Adam Karaoglu, Mert Asim Sinha, Soham Jang, Mingang Ha, Ho-Gun Jung, Kyungmin Gu, Kyeongmo Ullah, Ihsan Lee, Hyunki Šerých, Jonáš Neoral, Michal Matas, Jiří Zhou, Rulin He, Wenlong Wang, An Ren, Hongliang Silva, Bruno Queirós, Sandro Lima, Estêvão Vilaça, João L. Kikuchi, Shunsuke Kouno, Atsushi Matsuzaki, Hiroki Li, Tongtong Chen, Yulu Li, Ling Ma, Xiang Li, Xiaojian Zeinoddin, Mona Sheikh Wang, Xu Tandogdu, Zafer Shaw, Greg Mazomenos, Evangelos Stoyanov, Danail Chen, Yuxin Wu, Zijian Ladikos, Alexander DiMaio, Simon Salcudean, Septimiu E. Mohareri, Omid Intuitive Surgical Inc. Sunnyvale United States ImFusion GmbH Munich Germany Technical University of Munich Munich Germany NVIDIA Santa Clara United States Korea Republic of CMP Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic Shenzhen Research Institute China The Chinese University of Hong Kong China Shenzhen University China School of Medicine University of Minho Braga Portugal ICVS/3B’s - PT Government Associate Laboratory Braga Guimarães Portugal 2Ai –School of Technology IPCA Barcelos Portugal LASI – Associate Laboratory of Intelligent Systems Guimarães Portugal Jmees Inc Japan United States School of Management Hefei University of Technology Hefei230009 China Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education Hefei China Hawkes Institute University College London London United Kingdom Dept of Urology University College London Hospitals United Kingdom University of British Columbia Canada

Understanding tissue motion in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy. Labeled data are essential to enabling algorithms in these downstream tasks since they allow us to quantify and train algorithms. This paper introduces a point tracking challenge to address this, wherein participants can submit their algorithms for quantification. The submitted algorithms are evaluated using a dataset named surgical tattoos in infrared (STIR), with the challenge aptly named the STIR Challenge 2024. The STIR Challenge 2024 comprises two quantitative components: accuracy and efficiency. The accuracy component tests the accuracy of algorithms on in vivo and ex vivo sequences. The efficiency component tests the latency of algorithm inference. The challenge was conducted as a part of MICCai EndoVis 2024. In this challenge, we had 8 total teams, with 4 teams submitting before and 4 submitting after challenge day. This paper details the STIR Challenge 2024, which serves to move the field towards more accurate and efficient algorithms for spatial understanding in surgery. In this paper we summarize the design, submissions, and results from the challenge. The challenge dataset is available here: https://***/records/14803158, and the code for baseline models and metric calculation is available here: https://***/athaddius/STIRMetrics Copyright © 2025, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

The analysis for Gait Energy Image based on statistical methods

The analysis for Gait Energy Image based on statistical meth...

引用

2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016

作者： Rahman, Siti Zaharah Abd Abdullah, Siti Norul Huda Sheikh Nazri, Mohd Zakree Bin Ahmad Pattern Recognition Research Group Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Data Mining and Optimization Group Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia

ISBN: (纸本)9781509028894

Gait features representation is an important step in gait biometric recognition. It represents content of the individual image and the pattern of human walking simultaneously. Discriminative features can provide the most relevant and useful information for individual classification. Many state of the art feature fusions based on average silhouette were used for gait feature representation technique. Those fusion methods are mostly robust in simple case but inadequate for difficult gait representation such as walking with occlusion, walking with different view and walking with briefcase that affect the accuracy of gait performance. For that reason, we are exploring and proposing another potential feature fusion based on statistical method namely edges directed matrix of Gait Energy Image (EDMSGEI). We compare our EDMSGEI method with Gray Level Co-Occurrence Matrix (GLCMGEI) and Histogram of Gaussian (HOGGEI) method for individual recognition with K-Nearest neighbour classifier. The datasets involved are CASIA and UKM-CSM dataset images. Apart from HOGGEI, this study also shows that EDMSGEI gained better gait recognition performance. © 2016 IEEE.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

Neural gen feature selection for supervised learning classifier

引用

research Journal of Applied Sciences, Engineering and Technology 2014年第15期7卷 3181-3187页

作者： Abdulameer, Mohammed Hasan Sheikh Abdullah, Siti Norul Huda Othman, Zulaiha Ali Pattern Recognition Research Group Centre for Artificial Intelligence Technology Faculty of Information Science and Technology 43600 Bandar Baru Bangi Malaysia Data Mining and Optimization Group Faculty of Information System and Technology Universiti Kebangsaan Malaysia 43600 Bandar Baru Bangi Malaysia

Face recognition has recently received significant attention, especially during the past few years. Many face recognition techniques were developed such as PSO-SVM and LDA-SVM However, inefficient features in the face recognition may lead to inadequate in the recognition results. Hence, a new face recognition system based on Genetic Algorithm and FFBNN technique is proposed. Our proposed face recognition system initially performs the feature extraction and these optimal features are promoted to the recognition process. In the feature extraction, the optimal features are extracted from the face image database by Genetic Algorithm (GA) with FFBNN and the computed optimal features are given to the FFBNN technique to carry out the training and testing process. The optimal features from the feature database are fed to the FFBNN for accomplishing the training process. The well trained FFBNN with the optimal features provide the recognition result. The optimal features in FFBNN by GA efficiently perform the face recognition process. The human face dataset called YALE is utilized to analyze the performance of our proposed GA-FFNN technique and also this GA-FFBNN is compared with standard SVM and PSO-SVM techniques. © Maxwell Scientific Organization, 2014.

关键词： Face recognition FFBNN GA PCA SVM

来源：评论

学校读者我要写书评

暂无评论

Efficient Face recognition Technique with aid of Active Appearance Model

Efficient Face Recognition Technique with Aid of Active Appe...

引用

16th FIRA RoboWorld Congress, FIRA 2013

作者： Hasan, Mohammed Sheikh Abdullaha, Siti Norul Huda Othman, Zulaiha Ali Pattern Recognition Research Group Centre For Artificial Intelligence Technology Universiti Kebangsaan 43600 Bandar Baru Bangi Malaysia University of Kufa Iraq Data Mining and Optimization Group Universiti Kebangsaan 43600 Bandar Baru Bangi Malaysia

ISBN: (纸本)9783642404085

No one can deny the fact that face recognition systems, as one of the most adaptable systems in biometric facial recognition, has interestingly been one of the fields that draw researchers' attention to enhance the efficiency and efficacy of biometric applications. These researchers have mainly focused on the existed limitations such as extracting unique and differentiable features that are not disturbed by pose, as well as illuminations and other environmental and physical variations. As such, using an Active Appearance Model (AAM) is known to be a solution to extract features by precise modeling of human faces under various physical and environmental circumstances. This research paper tries to draw attention to using AAM based 1 to N face recognition system which the performance of such system can be seen in the experimental results. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Face recognition

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：