检索结果-内蒙古大学图书馆

NeuroPod: a real-time neuromorphic spiking CPG applied to robotics

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gutierrez-Galan, Daniel Dominguez-Morales, Juan P. Perez-Peña, Fernando Linares-Barranco, Alejandro Robotics and Computer Technology Lab Universidad de Sevilla Spain Department of Computer Architecture and Technology Universidad de Cádiz Spain

Initially, robots were developed with the aim of making our life easier, carrying out repetitive or dangerous tasks for humans. Although they were able to perform these tasks, the latest generation of robots are being designed to take a step further, by performing more complex tasks that have been carried out by smart animals or humans up to date. To this end, inspiration needs to be taken from biological examples. For instance, insects are able to optimally solve complex environment navigation problems, and many researchers have started to mimic how these insects behave. Recent interest in neuromorphic engineering has motivated us to present a real-time, neuromorphic, spike-based Central Pattern Generator of application in neurorobotics, using an arthropod-like robot. A Spiking Neural Network was designed and implemented on SpiNNaker. The network models a complex, online-change capable Central Pattern Generator which generates three gaits for a hexapod robot locomotion. Reconfigurable hardware was used to manage both the motors of the robot and the real-time communication interface with the Spiking Neural Networks. Real-time measurements confirm the simulation results, and locomotion tests show that NeuroPod can perform the gaits without any balance loss or added delay. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

Attention-driven dynamic graph convolutional network for multi-label image recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-label benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. All codes can be found at https://***/Yejin0111/ADD-GCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Group shift pointwise convolution for volumetric medical image segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Junjun Ye, Jin Li, Cheng Song, Diping Chen, Wanli Wang, Shanshan Gu, Lixu Qiao, Yu School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Shanghai AI Lab Shanghai China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Chinese University of Hong Kong Hong Kong Peng Cheng Laboratory Guangdong Shenzhen China Pazhou Lab Guangdong Guangzhou China

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models employing 3D convolutions introduce more trainable parameters and are more computationally complex, which may lead easily to model overfitting especially for medical applications with limited available training data. This paper aims to improve the effectiveness and efficiency of 3D convolutions by introducing a novel Group Shift Pointwise Convolution (GSP-Conv). GSP-Conv simplifies 3D convolutions into pointwise ones with 1 × 1 × 1 kernels, which dramatically reduces the number of model parameters and FLOPs (e.g. 27× fewer than 3D convolutions with 3 × 3 × 3 kernels). Naïve pointwise convolutions with limited receptive fields cannot make full use of the spatial image context. To address this problem, we propose a parameter-free operation, Group Shift (GS), which shifts the feature maps along different spatial directions in an elegant way. With GS, pointwise convolutions can access features from different spatial locations, and the limited receptive fields of pointwise convolutions can be compensated. We evaluate the proposed methods on two datasets, PROMISE12 and BraTS18. Results show that our method, with substantially decreased model complexity, achieves comparable or even better performance than models employing 3D convolutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Sleepposenet: Multi-View multi-task learning for sleep postural transition recognition using UWB

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Piriyajitakonkij, Maytus Warin, Patchanon Lakhan, Payongkit Leelaarporn, Pitsharponrn Pianpanit, Theerasarn Niparnan, Nattee Mukhopadhyay, Subhas Chandra Wilaiprasitporn, Theerawit Bio-inspired Robotics and Neural Engineering Lab School of Information Science and Technology Vidyasirimedhi Institute of Science & Technology Rayong Thailand Nakhon Nayok Thailand Computer Engineering Department Chulalongkorn University Bangkok Thailand School of Engineering Macquarie University SydneyNSW2109 Australia

Recognizing the movements during sleep is crucial for monitoring of patients with sleep disorders. However, the utilization of the deep learning approaches ultra-wideband (UWB)-based indoor applications for the classification of human sleeping postures has not been explored widely. This study investigates the performance of the off-the-shelf single antenna UWB in a novel application of sleep postural transition (SPT) recognition. The proposed Multi-View Multi-Task Learning, entitled SleepPoseNet or SPN, with time series data augmentation aims to classify four standard SPTs. SPN exhibits an ability to capture both time and frequency features, including the movement and direction of sleeping positions. Three cost functions for multi-views, multi-tasks, and classification are proposed to optimize SPN. The data recorded from 26 volunteers displayed that SPN with mean accuracy of 79.7±0.5% significantly outperformed the mean accuracy of 73.5 ± 0.7% obtained from deep convolution neural network (DCNN) in a recent state-of-the-art work on human activity recognition using UWB. Apart from UWB system, SPN with the data augmentation can ultimately be adopted to learn and classify time series data in various applications. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Conditional sequential modulation for efficient global image retouching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Korea Republic of University of Chinese Academy of Sciences China

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

TTPP: Temporal transformer with progressive prediction for efficient action anticipation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Wen Peng, Xiaojiang Su, Yanzhou Qiao, Yu Cheng, Jian School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Reliable and Balanced Transfer Learning for Generalized Multimodal Face Anti-Spoofing

学校读者我要写书评

暂无评论

IEEE transactions on pattern analysis and machine intelligence 2025年 PP卷 PP页

作者： Xun Lin Ajian Liu Zitong Yu Rizhao Cai Shuai Wang Yi Yu Jun Wan Zhen Lei Xiaochun Cao Alex Kot Beihang University School of Computer Science and Engineering Beijing China Beijing China Great Bay University Dongguan China Lab Singapore Macau University of Science and Technology Taipa China School of Artificial Intelligence Beijing China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Hong Kong Shenzhen Campus of Sun Yat-sen University Shenzhen China

Face Anti-Spoofing (FAS) is essential for securing face recognition systems against presentation attacks. Recent advances in sensor technology and multimodal learning have enabled the development of multimodal FAS systems. However, existing methods often struggle to generalize to unseen attacks and diverse environments due to two key challenges: (1) Modality unreliability, where sensors such as depth and infrared suffer from severe domain shifts, impairing the reliability of cross-modal fusion; and (2) Modality imbalance, where over-reliance on a dominant modality weakens the model's robustness against attacks that affect other modalities. To overcome these issues, we propose MMDG++, a multimodal domain-generalized FAS framework built upon the vision-language model CLIP. In MMDG++, we design the Uncertainty-Guided Cross-Adapter++ (U-Adapter++) to filter out unreliable regions within each modality, enabling more reliable multimodal interactions. Additionally, we introduce Rebalanced Modality Gradient Modulation (ReGrad) for adaptive gradient modulation to balance modality convergence. To further enhance generalization, propose Asymmetric Domain Prompts (ADPs) that leverage CLIP's language priors to learn generalized decision boundaries across modalities. We also develop a novel multimodal FAS benchmark to evaluate generalizability under various deployment conditions. Extensive experiments across this benchmark show our method outperforms state-of-the-art FAS methods, demonstrating superior generalization capability.

关键词： Visual languages

Upper limb human-exoskeleton system motion state classification based on semg: application of CNN-BiLSTM-attention model

学校读者我要写书评

暂无评论

Scientific reports 2025年第1期15卷 18969页

作者： Dongwei Zhao Xiangming Ye Song Wang Chenfeng Zhang Shouqian Sun Xuequn Zhang Ruidong Cheng College of Computer Science and Technology Zhejiang University Hangzhou China. Center for Rehabilitation Medicine Department of Rehabilitation Medicine Zhejiang Provincial People's Hospital (Affiliated People's Hospital Hangzhou Medical College) Zhejiang Engineering Research Center for Digital-Intelligent Rehabilitation Equipment Hangzhou China. Innovation Center of Yangtze River Delta Zhejiang University Jiaxing China. College of Computer Science and Technology Zhejiang University Hangzhou China. ssq@***. Kuntai Exobot&Wibot Lab Taizhou Mintai Robotics Co. LTD Taizhou China.

This study aims to classify five typical motion states of the human upper limb based on surface electromyography signals, thereby supporting the real-time control system of an assistive upper limb exoskeleton. We propose a deep learning model combining convolutional neural networks, bidirectional long short-term memory networks, and attention mechanism to enhance the accuracy of motion state recognition in complex scenarios. Surface electromyography data were collected from ten participants for the biceps, triceps, and deltoid muscles, covering five representative states: resting, mild activity, rapid movement, dynamic load-bearing, and static load-bearing. Following the systematic fusion of multi-domain features spanning time, morphological, frequency, and cepstral characteristics, temporal features were structured through sliding window segmentation to serve as inputs for the proposed model. The proposed model achieved a classification accuracy of 97.29% on the test set, with an average accuracy of 88.17 ± 5.39% under leave-one-subject-out cross-validation, outperforming baseline algorithms. These findings highlight the model's potential in motion state classification, facilitating advanced, intelligent control capabilities of human-exoskeleton systems.

关键词： Bidirectional long short-term memory network Motion classification Surface electromyography Upper limb exoskeleton

Virtual Control Contraction Metrics: Convex Nonlinear Feedback Design via Behavioral Embedding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Ruigang Tóth, Roland Koelwijn, Patrick J.W. Manchester, Ian R. Australian Centre for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW2006 Australia Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Systems and Control Lab Institute for Computer Science and Control Budapest Hungary

This paper presents a systematic approach to nonlinear state-feedback control design that has three main advantages: (i) it ensures exponential stability and L2-gain performance with respect to a user-defined set of reference trajectories, and (ii) it provides constructive conditions based on convex optimization and a path-integral-based control realization, and (iii) it is less restrictive than previous similar approaches. In the proposed approach, first a virtual representation of the nonlinear dynamics is constructed for which a behavioral (parameter-varying) embedding is generated. Then, by introducing a virtual control contraction metric, a convex control synthesis formulation is derived. Finally, a control realization with a virtual reference generator is computed, which is guaranteed to achieve exponential stability and L2-gain performance for all trajectories of the targeted reference behavior. We show that the proposed methodology is a unified generalization of the two distinct categories of linear-parameter-varying (LPV) state-feedback control approaches: global and local methods. Moreover, it provides rigorous stability and performance guarantees as a method for nonlinear tracking control, while such properties are not guaranteed for tracking control using standard LPV approaches. © 2020, CC BY.

关键词： Convex optimization