检索结果-内蒙古大学图书馆

1st International Workshop on Multimedia Computing for Urban Data, UrbanMM 2021, co-located with ACM Multimedia 2021

作者： Tan, Xun Chen, Xingyu Zhang, Guowei Ding, Jishiyu Lan, Xuguang Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics The Second Academy of CASIC Beijing China

ISBN: (纸本)9781450386692

Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to their different characteristics and the interference from the non-interest areas. To solve this problem, we propose a Multi-Branch Deep Fusion Network (MBDF-Net) for 3D object detection. The proposed detector has two stages. In the first stage, our multi-branch feature extraction network utilizes Adaptive Attention Fusion (AAF) modules to produce cross-modal fusion features from single-modal semantic features. In the second stage, we use a region of interest (RoI) -pooled fusion module to generate enhanced local features for refinement. A novel attention-based hybrid sampling strategy is also proposed for selecting key points in the downsampling process. We evaluate our approach on two widely used benchmark datasets including KITTI and SUN-RGBD. The experimental results demonstrate the advantages of our method over state-of-the-art approaches. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

BLE beacons for sample position estimation in a life science automation laboratory

引用

Transportation Safety and Environment 2024年第3期6卷 111-123页

作者： Haiping Wu Steffen Junginger Thomas Roddelkopf Hui Liu Kerstin Thurow Institute of Artificial Intelligence&Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075HunanChina Institute of Automation(IAT) University of Rostock18119 RostockGermany Center of Life Science Automation(celisca) University of Rostock18119 RostockGermany

Estimation of the sample position is essential for working process monitoring and management in the life science automation lab*** low-energy(BLE)beacons have the advantages of low price,small size and low energy consumption,which make them a promising solution for sample position estimation in the automated *** fingerprinting models have been proposed to achieve indoor localization with the received signal strength(RSS)***,most of the research depends on intensive beacon *** estimation,which depends entirely on one beacon,is more suitable for sample position estimation in large automated *** complexity of the life science automation laboratory environment brings challenges to the traditional path loss model(PLM),which is a widely used radio wave propagation model-based proximity estimation *** this paper,BLE sensing devices for sample position estimation are *** BLE beacon-based proximity estimation is discussed in the framework of machine learning,in which the support vector regression(SVR)is utilized to model the nonlinear relationship between the RSS data and distance,and the Kalman filter is utilized to decrease the RSS data *** experimental results over different environments indicate that the SVR outperforms the PLM significantly,and provides 1 m absolute errors for more than 95%of the testing *** Kalman filter brings benefits to stable distance *** from proximity-based sample position estimation,the proposed framework turned out to be effective in position estimation between parallel workbenches and position estimation on an automated workstation.

关键词： BLE beacon position estimation proximity estimation received signal strength(RSS) support vector regression(SVR) life science automation laboratory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control of Global Trajectory Tracking for a Tractor-Trailer System with Wheeltrack Uncertainties

Adaptive Control of Global Trajectory Tracking for a Tractor...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Su, Yuanhao Wu, Qingxiang Sun, Ning He, Chunhui Sun, Haosheng Institute of Robotics and Automatic Information Systems College of Artificial Intelligence China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China

ISBN: (纸本)9781665481090

Given the increasing number of transportation tasks, a multisection tractor-trailer system is an ideal choice. To extend the application scope and adapt more complex workspace for tractor-trailer systems, this paper presents a global trajectory tracking controller for an off-axis tractor-trailer system with variable wheeltrack using adaptive method. Considering the tracking errors caused by the variation of wheeltrack, an online adaptive parameter update law is proposed to estimate the unknown wheeltrack and achieve tracking robustness. Simulation results demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Tractors (truck)

来源：评论

学校读者我要写书评

暂无评论

Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10648-10662页

作者： Zhen Cheng Fei Zhu Xu-Yao Zhang Cheng-Lin Liu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Science Park Hong Kong

Detecting out-of-distribution (OOD) inputs has been a critical issue for neural networks in the open world. However, the unstable behavior of OOD detection along the optimization trajectory during training has not been explored clearly. In this article, we first find the performance of OOD detection suffers from overfitting and instability during training: 1) the performance could decrease when the training error is near zero and 2) the performance would vary sharply in the final stage of training. Based on our findings, we propose an average of pruning (AoP), consisting of model averaging (MA) and pruning, to mitigate the unstable behaviors. Specifically, MA can help achieve a stable performance by smoothing the landscape, and pruning is theoretically and empirically verified to eliminate overfitting by avoiding redundant features. Comprehensive experiments on various datasets and architectures are conducted to verify the effectiveness of our method.

关键词： Training Overfitting Data models Perturbation methods Visualization Training data Noise measurement Transformers Trajectory Reliability

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Camera and One-beam LiDAR Fusion Network for Low-cost 3D Object Detection

Multi-modal Camera and One-beam LiDAR Fusion Network for Low...

引用

IEEE International Conference on robotics and Biomimetics

作者： Rongxin Wang Ronghai Chen Meng Yang Xuguang Lan Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University P.R. China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

3D object detection is a fundamental technique for scene perception of autonomous robots. Recent methods rely heavily on muti-beam LiDAR such as 64-beam, which is limited by the cost and power in practical applications. Monocular camera or one-beam LiDAR provides optional ways for this problem. However, the front one is inherently ill-posed in depth prediction and the latter one could not well infer semantics, size and pose of 3D objects. In addition, the fusion of camera and one-beam LiDAR is not well studied in recent methods. We specifically investigate a framework of 3D object detection by fusing monocular camera and one-beam LiDAR. Different from recent multi-modal techniques, which primarily rely on LiDAR data, our solution mainly utilizes camera to detect 3D objects and one-beam LiDAR as a supplement. First, a high-quality depth map is predicted from an RGB image and one-beam LiDAR points with a two-branch network and a global-local normal gradient loss. Second, pseudo-LiDAR points are converted from the depth map and further corrected by the one-beam LiDAR points. Finally, corrected pseudo-LiDAR points are fed into a mature LiDAR-based 3D detector. Our method is verified on KITTI test set and compared to twelve recent baselines of LiDAR-based, RGB-based and multi-modal methods. Extensive results verify that our method achieves 38.00, 27.36 and 22.92 of AP40 $(\text{IoU}=0.7)$ in easy, moderate and hard modes, which significantly outperforms all the baselines.

关键词： Laser radar Three-dimensional displays Costs Biomimetics Robot vision systems Semantics Object detection Detectors Cameras Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Under-Display ToF Imaging with Efficient Transformer

Under-Display ToF Imaging with Efficient Transformer

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Yuan Sun Hao Wei Xin Qiao Pengchao Deng Chenyang Ge Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Demand for full screen in consumer electronics has propelled the development of under-display image processing. For time-of-flight cameras, they are usually placed under TOLED display. Due to the presence of pixels and display patterns in the TOLED panel, depth maps from under-display time-of-flight (UD-ToF) are noisy, blurry, and inaccurate. We propose a non-local method based on Vision Transformer for UD-ToF depth restoration to address these issues. Specifically, a novel feature attention block is designed to incorporate non-local depth features. Additionally, we take ToF raw measurements rather than the depth map as input, allowing the network to extract informative features from the raw domain. We conduct comprehensive experiments on real RUD-TOF and synthetic SUD-TOF benchmark datasets, and the results indicate that the proposed transformer-based method achieves better performance than the state-of-the-art algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Voxel Mamba: group-free state space models for point cloud based 3D object detection 24

Voxel Mamba: group-free state space models for point cloud b...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Guowen Zhang Lue Fan Chenhang He Zhen Lei Zhaoxiang Zhang Lei Zhang The Hong Kong Polytechnic University and Centre for Artificial Intelligence and Robotics HKISI CAS Institute of Automation Chinese Academy of Sciences The Hong Kong Polytechnic University Centre for Artificial Intelligence and Robotics HKISI CAS and Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences

ISBN: (纸本)9798331314385

Serialization-based methods, which serialize the 3D voxels and group them into multiple sequences before inputting to Transformers, have demonstrated their effectiveness in 3D object detection. However, serializing 3D voxels into 1D sequences will inevitably sacrifice the voxel spatial proximity. Such an issue is hard to be addressed by enlarging the group size with existing serialization-based methods due to the quadratic complexity of Transformers with feature sizes. Inspired by the recent advances of state space models (SSMs), we present a Voxel SSM, termed as Voxel Mamba, which employs a group-free strategy to serialize the whole space of voxels into a single sequence. The linear complexity of SSMs encourages our group-free design, alleviating the loss of spatial proximity of voxels. To further enhance the spatial proximity, we propose a Dual-scale SSM Block to establish a hierarchical structure, enabling a larger receptive field in the 1D serialization curve, as well as more complete local regions in 3D space. Moreover, we implicitly apply window partition under the group-free framework by positional encoding, which further enhances spatial proximity by encoding voxel positional information. Our experiments on Waymo Open Dataset and nuScenes dataset show that Voxel Mamba not only achieves higher accuracy than state-of-the-art methods, but also demonstrates significant advantages in computational efficiency. The source code is available at https://***/gwenzhang/Voxel-Mamba.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using External Attention in Vision-based Autonomous Driving

Using External Attention in Vision-based Autonomous Driving

引用

2021 China Automation Congress, CAC 2021

作者： Meng, Xiangning Xue, Jianru Zhao, Kang Li, Gengxin Institute of Artificial Intelligence and Robotics College of Artificial Intelligence Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9781665426473

Imitation learning (IL) method provides a concise framework for autonomous driving, and it learns the policy from human demonstration via mapping from sensor data to vehicle controls. However, how to achieve effective learning is an ongoing challenge in driving policy learning. A feasible solution is to introduce attention mechanism, which enables the deep model focus on the features related to the driving task. In this paper, we propose to train a driving policy model with latest external attention joining the policy network as blocks. The experimental results on CARLA driving benchmark demonstrate our external attention guided driving policy model has better performance and costs less training time than the model without attention mechanism. Moreover, our method outperforms the state-of-the-arts self-attention driving policy methods. © 2021 IEEE

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision

Elevating Skeleton-Based Action Recognition with Efficient M...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yiping Wei Kunyu Peng Alina Roitberg Jiaming Zhang Junwei Zheng Ruiping Liu Yufan Chen Kailun Yang Rainer Stiefelhagen Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Institute for Artificial Intelligence University of Stuttgart Germany School of Robotics Hunan University China

Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a multi-modality setup. These works overlooked the differences in performance among modalities, which led to the propagation of erroneous knowledge between modalities while only three fundamental modalities, i.e., joints, bones, and motions are used, hence no additional modalities are *** this work, we first propose an Implicit Knowledge Exchange Module (IKEM) which alleviates the propagation of erroneous knowledge between low-performance modalities. Then, we further propose three new modalities to enrich the complementary information between modalities. Finally, to maintain efficiency when introducing new modalities, we propose a novel teacher-student framework to distill the knowledge from the secondary modalities into the mandatory modalities considering the relationship constrained by anchors, positives, and negatives, named relational cross-modality knowledge distillation. The experimental results demonstrate the effectiveness of our approach, unlocking the efficient use of skeleton-based multi-modality data. Source code will be made publicly available at https://***/desehuileng0o0/IKEM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

arXiv

引用

arXiv 2023年

作者： Jiang, Jingjing Zheng, Nanning Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Recently, finetuning pretrained Vision-Language Models (VLMs) has been a prevailing paradigm for achieving state-of-the-art performance in Visual Question Answering (VQA). However, as VLMs scale, finetuning full model parameters for a given task in low-resource settings becomes computationally expensive, storage inefficient, and prone to overfitting. Current parameter-efficient tuning methods dramatically reduce the number of tunable parameters, but there still exists a significant performance gap with full finetuning. In this paper, we propose MixPHM, a redundancy-aware parameter-efficient tuning method that outperforms full finetuning in low-resource VQA. Specifically, MixPHM is a lightweight module implemented by multiple PHM-experts in a mixture-of-experts manner. To reduce parameter redundancy, MixPHM reparameterizes expert weights in a low-rank subspace and shares part of the weights inside and across experts. Moreover, based on a quantitative redundancy analysis for adapters, we propose Redundancy Regularization to reduce task-irrelevant redundancy while promoting task-relevant correlation in MixPHM representations. Experiments conducted on VQA v2, GQA, and OK-VQA demonstrate that MixPHM outperforms state-of-the-art parameter-efficient methods and is the only one consistently surpassing full finetuning. Copyright © 2023, The Authors. All rights reserved.

关键词： Redundancy

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：