检索结果-内蒙古大学图书馆

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Chen, Yirong Fan, Weiquan Xing, Xiaofen Pang, Jianxin Huang, Minlie Han, Wenjing Tie, Qianfeng Xu, Xiangmin The UBTECH-SCUT Joint Research Lab Engineering Research Center Ministry of Education on Human Body Data Perception School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China UBTECH Robotics Corp Shenzhen518000 China CoAI Group State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers’ personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It’s difficult for dialogue systems to understand speakers’ personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers’ personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available1 © 2022, CC BY-NC-SA.

关键词： Emotion Recognition

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Yirong Fan, Weiquan Xing, Xiaofen Pang, Jianxin Huang, Minlie Han, Wenjing Tie, Qianfeng Xu, Xiangmin The UBTECH-SCUT Joint Research Lab Engineering Research Center of Ministry of Education on Human Body Data Perception School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China UBTECH Robotics Corp Shenzhen518000 China CoAI Group State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers' personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It's difficult for dialogue systems to understand speakers' personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available. © 2022, CC BY-NC-ND.

关键词： Speech processing

Beyond photometric consistency: Gradient-based dissimilarity for improving visual odometry and stereo matching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Quenzel, Jan Rosu, Radu Alexandru Läbe, Thomas Stachniss, Cyrill Behnke, Sven Intelligent Systems Group University of Bonn Germany Robotics and Photogrammetry Lab. Institute of Geodesy and Geoinformation University of Bonn Germany

Pose estimation and map building are central ingredients of autonomous robots and typically rely on the registration of sensor data. In this paper, we investigate a new metric for registering images that builds upon on the idea of the photometric error. Our approach combines a gradient orientation-based metric with a magnitude-dependent scaling term. We integrate both into stereo estimation as well as visual odometry systems and show clear benefits for typical disparity and direct image registration tasks when using our proposed metric. Our experimental evaluation indicats that our metric leads to more robust and more accurate estimates of the scene depth as well as camera trajectory. Thus, the metric improves camera pose estimation and in turn the mapping capabilities of mobile robots. We believe that a series of existing visual odometry and visual SLAM systems can benefit from the findings reported in this paper. Copyright © 2020, The Authors. All rights reserved.

关键词： Photometry

Learning quadrupedal locomotion over challenging terrain

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lee, Joonho Hwangbo, Jemin Wellhausen, Lorenz Koltun, Vladlen Hutter, Marco Robotic Systems Lab ETH Zurich Zurich Switzerland Robotics and Artificial Intelligence Lab KAIST Daejeon Korea Republic of Intelligent Systems Lab Intel Santa ClaraCA United States

Some of the most challenging environments on our planet are accessible to quadrupedal animals but remain out of reach for autonomous machines. Legged locomotion can dramatically expand the operational domains of robotics. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have escalated in complexity while falling short of the generality and robustness of animal locomotion. Here we present a radically robust controller for legged locomotion in challenging natural environments. We present a novel solution to incorporating proprioceptive feedback in locomotion control and demonstrate remarkable zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. It is based on a neural network that acts on a stream of proprioceptive signals. The trained controller has taken two generations of quadrupedal ANYmal robots to a variety of natural environments that are beyond the reach of prior published work in legged locomotion. The controller retains its robustness under conditions that have never been encountered during training: deformable terrain such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work opens new frontiers for robotics and indicates that radical robustness in natural environments can be achieved by training in much simpler domains. Copyright © 2020, The Authors. All rights reserved.

关键词： Controllers

Towards a probabilistic approach for quantifying uncertainty in robot soft tissue indentation via computational biomechanics models

学校读者我要写书评

暂无评论

Towards a probabilistic approach for quantifying uncertainty...

Australasian Conference on robotics and Automation 2019, ACRA 2019

作者： Montenegro, Jonathan A.Y. Singh, Surya P.N. Wittek, Adam Robotics Design Lab University of Queensland Brisbane Australia Intelligent Systems for Medicine Laboratory University of Western Australia Perth Australia

In surgical robot simulation and motion planning a forward (or predictive) model is critical. This paper considers an initial approach to estimate the effect of the variation of parameters on the overall statistical distribution for the total strain and stress as predicted by a non-linear biomechanical model. This considers the statistical distribution, as compared to a single mean value, of the predicted variables. For example, if the material were an ideal a Hookean spring (i.e., F = kx), then Gaussian variations in force (F ∼ N (μF , σF2 )) and material stiffness (k ∼ N (μk, σk2 )) would give a Ratio distribution in displacement x (i.e., the distribution formed from the ratio of two Gaussians). In order to evaluate the case when the material properties are non-linear, such as those for brain tissue, this paper explores an empirical approach based around a sequence of multiple cases where the strain was determined via FEA. When assuming an Ogden hyperelastic constitutive model, results show a Normal variation of displacement for Normal varying moduli, but a Bimodal distribution of displacement for Normal varying forces. © 2019 Australasian robotics and Automation Association. All rights reserved.

关键词： Motion planning

Correction to: Regional optimum frequency analysis of resting-state fMRI data for early detection of Alzheimer’s disease biomarkers

学校读者我要写书评

暂无评论

Multimedia Tools and Applications 2022年第6期82卷 9551-9552页

作者： Garg, Gaurav Prasad, Girijesh Garg, Lalit Miyakoshi, Makoto Nakai, Toshiharu Coyle, Damien Embedded & Robotics BrainAlive Research Pvt. Ltd Kanpur India School of Computing and Intelligent Systems Magee Campus Ulster University Londonderry UK Faculty of Information & Communication Technology University of Malta Msida Malta Swartz Center for Computational Neuroscience Institute for Neural Computation University of California San Diego San Diego USA Neuroimaging & Informatics Lab (Niinf) National Centre for Geriatrics and Gerontology (NCGG) Obu Japan

A moving target detection and localization strategy based on optical flow and pin-hole imaging methods using monocular vision

学校读者我要写书评

暂无评论

A moving target detection and localization strategy based on...

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wang, Shun Guo, Qingqiang Xu, Sheng Su, Dan School of Control Science and Engineering Shandong University Shandong Jinan250061 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Orbbec Inc. Shenzhen518057 China

ISBN: (纸本)9781665436786

This paper proposes a new strategy for moving target detection and localization based on monocular vision. Firstly, to detect a moving target with large displacement and high speed accurately, two consecutive video images captured by a monocular camera are preprocessed using the enhancement and denoising methods. Then, the optical flow representing motion information is calculated iteratively by the modified Lucas-Kanade optical flow method. Secondly, a new interest region extraction method is developed to overcome the negative impacts caused by the noises in the background. Specifically, this proposed method combines a two-level image segmentation strategy from coarse to fine, including median filtering, two-direction dynamic threshold segmentation, the Otsu method, and morphological processing. Thirdly, a low computational cost target localization algorithm is proposed based on pin-hole imaging theory. Besides, it only uses two-dimensional image and camera parameters to obtain the moving target's position in the three-dimensional space. Finally, experimental results show that the proposed strategy can effectively eliminate noise interferences and realize moving target detection, extraction, and localization. © 2021 IEEE.

关键词： Image segmentation

Deep learning in brain computer interfaces 19

学校读者我要写书评

暂无评论

Deep learning in brain computer interfaces

9th Balkan Conference in Informatics, BCI 2019

作者： Georgieva, Petia University of Aveiro Department of Electronics Telecommunications and Informatics Institute of Electronics and Informatics Engineering of Aveiro -Intelligent Robotics and Systems Lab Aveiro Portugal

ISBN: (纸本)9781450371933

Deep Learning (DL) refers to computational models composed of multiple processing layers capable of learning representations of data with multiple levels of abstraction [1]. Since the seminal work of Lecun et al. [2] on training convolutional networks using back-propagation and gradient-based optimization, DL has outperformed other machine learning techniques in many domains of science and industry. Hinton et al. [3], achieved breakthrough on the task of automatic speech recognition, the first major DL industrial application. DL has achieved great success in recognition tasks within a wide range of applications including computer vision (images, videos), natural language processing (text), bioinformatics, to mention a few. © 2019 Association for Computing Machinery.

关键词： Convolution

Describing Physics For Physical Reasoning: Force-based Sequential Manipulation Planning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Toussaint, Marc Ha, Jung-Su Driess, Danny Machine Learning & Robotics Lab University Stuttgart Stuttgart70569 Germany Max Planck Institute for Intelligent Systems Stuttgart70569 Germany

Physical reasoning is a core aspect of intelligence in animals and humans. A central question is what model should be used as a basis for reasoning. Existing work considered models ranging from intuitive physics and physical simulators to contact dynamics models used in robotic manipulation and locomotion. In this work we propose path descriptions of physics which directly allow us to leverage optimization methods to solve planning problems, using multi-physics descriptions that enable the solver to mix various levels of abstraction and simplifications for different objects and phases of the solution. We demonstrate the approach on various robot manipulation planning problems, such as grasping a stick in order to push or lift another object to a target, shifting and grasping a book from a shelve, and throwing an object to bounce towards a target. Copyright © 2020, The Authors. All rights reserved.

关键词：