检索结果-内蒙古大学图书馆

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Yang, Kuan Fang, Jianwu Zhu, Tong Xue, Jianru College of Transportation Engineering Chang’an University Xi’an China The Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9789819710867

Road accident classification which is an essential but rarely explored problem in the safe driving field. The core issue of accident classification is to learn the feature representation for partitioning different kinds of accidents. Compared with accident detection or anticipation only with occurrence probability, feature representation learning in accident classification is more challenging because of the extremely imbalanced accident categories. In addition, the severe light or weather conditions, various occasions, and complex crashing-object movement exacerbate the challenges. In this work, we form a text-video benchmark for fine-grained road accident classification (named Accident-CLIP). Accident-CLIP owns 13,669 dashcam videos with 58 kinds of accidents, where each accident is annotated with the text description of the accident type and the accident window. In the benchmarking stage, six state-of-the-art methods are evaluated from different video frame sampling methods, frame mixup strategy, input frame length, and the adaptation for long-tailed accident distribution. From experiments, we observe that current video classification models need a large space (the best Top-1 value is 41.39% on 2000 testing videos) to adapt to the extremely imbalanced road accident classification, and the formed Accident-CLIP benchmark provides a promising evaluation platform. © Beijing HIWING Scientific and Technological Information institute 2024.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Tiny Det: accurately detecting small objects within 1 GFLOPs

引用

Science China(Information Sciences) 2023年第1期66卷 318-319页

作者： Shaoyu CHEN Tianheng CHENG Jiemin FANG Qian ZHANG Yuan LI Wenyu LIU Xinggang WANG School of Electronic Information and Communications Huazhong University of Science and Technology Institute of Artificial Intelligence Huazhong University of Science and Technology Horizon Robotics Inc. Google Inc.

Dear editor,Object detection plays an important role in computer vision,and has gradually become the technical foundation of many applications. However, the inference procedure of advanced detection models requires ma... 详细信息

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Abusive Activity Detection with Multi-Modality Based on Convolutional Neural Network 48

Abusive Activity Detection with Multi-Modality Based on Conv...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Kim, Jisoo Ahn, Hyebin Yoo, Byounghyun Korea Institute of Science and Technology Center for Artificial Intelligence Korea Republic of Korea University of Science and Technology Artificial Intelligence and Robotics Kist School Korea Republic of

ISBN: (纸本)9781728163277

Abusive activity frequently occurs in various places, including nursing homes for the elderly. However, it is difficult to detect because it has various forms and is not easy to define. Therefore, in this study, we try to detect using the Convolutional Neural Network (CNN). Data based on multimodality (image and sound) was used to improve detection performance. In case of the image, a Motion History Image (MHI) was used to reflect motion information. The developed multi-modality-based detection system showed a performance of 0.807 (Accuracy) and 0.858 (F1 score). By comparing with the system using only image or sound, there is an improvement of 0.132 ~ 0.17 (Accuracy) and 0.094 ~ 0.138 (F1 score) © 2023 IEEE.

关键词： Abusive Activity Detection Convolutional Neural Network Motion History Image Multi-modality

来源：评论

学校读者我要写书评

暂无评论

Efficient Matrix-Based Multi-view Projection Features Combined for Multi-modal 3D Semantic Segmentation 21st

Efficient Matrix-Based Multi-view Projection Features Combin...

引用

21st Pacific Rim International Conference on artificial intelligence, PRICAI 2024

作者： Zhao, Jiayu Wei, Fei-Fei Liang, Anqi Mei, Kuizhi College of Artificial Intelligence Xi’an Jiaotong University Xi’an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9789819601219

This paper introduces BFVTModel, an efficient 3D semantic segmentation Model. Multi-modal segmentators, which employ LiDAR and Camera sensors as input, have gained popularity owing to their capacity to leverage the semantic information in image data and complementary details in point cloud data. However, the segmentation model using multi-modal input faces some problems, such as the modal consistency problem and the model complexity problem. In this paper, we propose utilizing the idea of an Occupancy-based multi-view feature combination method to obtain the 3D information of the features of the two modalities independently. We also design a projection structure to obtain the three-axis features in different modalities according to the information, including the main view, side view, and top view features. We construct a module called Feature View Transform (FVT) that combines three-axis plane features with bias. The CNN neural network is used to replace attention mechanisms, reducing the dimensionality of the original three-dimensional space matrix, thereby reducing the parameter count and increasing the model’s speed. We used a bilinear mapping structure to fuse LiDAR and Camera features and complete the 3D semantic segmentation task. We validate the model on the NuScenes dataset and obtain competitive accuracy results while leading the way in efficiency evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The effects of 17β-trenbolone and bisphenol A on sexual behavior and social dominance via the hypothalamic-pituitary-gonadal axis in male mice

引用

Journal of Environmental Sciences 2025年第5期151卷 54-67页

作者： Xiang Zuo Minghe Sun Huijuan Bai Shuhui Zhang Jialu Luan Qian Yu Zhenhua Fu Qili Zhao Mingzhu Sun Xin Zhao Xizeng Feng College of Life Science State Key Laboratory of Medicinal Chemical BiologyThe Key Laboratory of Bioactive MaterialsMinistry of EducationNankai UniversityTianjin 300071China Institute of Robotics&Automatic Information System College of Artificial IntelligenceNankai UniversityTianjin 300071China

17β-Trenbolone(17-TB)is well documented as an environmental endocrine disruptor in aquatic biological studies,but its effects on mammals remain poorly ***,17-TB acts as a hormone with properties similar to testosterone,and the consequences of juvenile exposure on adult social behavior remain *** A(BPA)acts as an estrogen-like hormone,compared to ***-week-old male Balb/c mice were exposed orally to 17-TB(100μg/(kg·day))and BPA(4 mg/(kg·day))for 28 *** of social interactions and a three-chamber test showed that 17-TB increased virility in male mice,intensified both male and female sexual behavior,and attracted and accepted female *** also increased social dominance through tube tests inmalemice and markedly activated the c-Fos^(+)immune response in themedial prefrontal cortex(mPFC)and basal amygdala(BLA).ELISA data showed that 17-TB and BPA exposure significantly affected serum gonadotropin-releasing hormone(GnRH),growth hormone(GH),estradiol(E2),and luteinizing hormone(LH)levels,as well as testicular lesions and androgen receptor(ARβ)and estrogen receptor(ERα)*** transcriptomic analysis further confirmed that could disrupt steroid synthesis and linoleic acid-related biometabolic *** findings suggest the influence of 17-TB and BPA exposure on sexual behavior and fertility in male mice,possibly through modulation of the hypothalamic-pituitary-gonadal *** study provides insights relevant to human reproductive health and neuro-social behavioral research,and the potential risk of environmental disturbances should not be overlooked.

关键词： 17β-Trenbolone(17-TB) Bisphenol A(BPA) hypothalamic-pituitary-gonadal axis(HPG) Sex hormones Social dominance Sexual behavior

来源：评论

学校读者我要写书评

暂无评论

Thin and Flexible Breeze-Sense Generators for Non-Contact Haptic Feedback in Virtual Reality

引用

Nano-Micro Letters 2025年第6期17卷 397-410页

作者： Kaijun Zhang Zhe Liu Yexi Zhou Zhaoyang Li Dazhe Zhao Xiao Guan Tianjun Lan Yanting Gong Bingpu Zhou Junwen Zhong Department of Electromechanical Engineering and Centre for Artificial Intelligence and Robotics University of MacaoMacao SAR 999078People’s Republic of China Joint Key Laboratory of the Ministry of Education Institute of Applied Physics and Materials EngineeringUniversity of MacaoMacao SAR 999078People’s Republic of China

In the realm of virtual reality(VR),haptic feedback is integral to enhance the immersive experience;yet,existing wearable devices predominantly rely on skin contact feedback,lacking options for compact and non-contact breeze-sense ***,we propose a compact and non-contact working model piezoelectret actuator for providing a gentle and safe breeze *** easy-fabricated and flexible breeze-sense generator with thickness around 1 mm generates air flow pressure up to~163 Pa,which is significantly sensed by human *** a typical demonstration,the breeze-sense generators array showcases its versatility by employing multiple coded modes for non-contact information *** thin thinness and good flexibility facilitate seamless integration with wearable VR setups,and the wearable arrays empower volunteers to precisely perceive the continuous and sudden breeze senses in the virtual *** work is expected to inspire developing new haptic feedback devices that play pivotal roles in human-machine interfaces for VR applications.

关键词： Virtual reality Wearable electronics Non-contact haptic feedback Breeze-sense Piezoelectret actuator

来源：评论

学校读者我要写书评

暂无评论

Design of a Convertible Autonomous Sailboat

Design of a Convertible Autonomous Sailboat

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Lin, Bairun Liang, Cheng Zhang, Lianxin Qian, Huihuan Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China The Chinese University of HongKong Shenzhen China

ISBN: (纸本)9798350327182

Multihull sailboats have significantly improved stability but poor maneuverability compared to monohull sailboats under the same conditions. Therefore, this article proposes a convertible autonomous sailboat based on the transformation of an autonomous sailboat. This article analyzes and studies stability improvements that validate our design and analysis in calm and turbulent water. It turns out that in the absence of waves, compared to autonomous sailboats, our convertible autonomous sailboat has a speed loss in the range of 25% to 30%, but its stability improved by 84.13% to 88.77%. However, in the presence of waves, the velocity loss is only 15.56% to 24.44%, but the stability improved by 92.37% to 94.78% © 2023 IEEE.

关键词： Stability

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 38

Voxel Mamba: Group-Free State Space Models for Point Cloud b...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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

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. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Group UAV Navigation by Qualifying Human-Machine Decisions in Hybrid Reinforcement Learning

Group UAV Navigation by Qualifying Human-Machine Decisions i...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Xuyang Fang, Jianwu Du, Kai Xue, Jianru Chang'An University Xi'an China Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University Xi'an China

ISBN: (纸本)9798350303759

In this paper, we focus on the continuous control of Unmanned Aerial Vehicle (UAV) group in large-scale 3D complex environment based on deep reinforcement learning (DRL) method. The purpose is to make the UAV group safely reach the random target area from a certain starting point, and the flight height and speed are variable during the navigation process. In this paper, a DRL framework combining the human-in-the-loop method is designed. The UAV group is preformed into a mobile whole, and the sensor data of the UAV group is directly mapped to the control signal. The role of human-in-the-loop is to switch the human-machine control right if necessary, so that humans can intervene and correct the dangerous actions of the agent. Based on this framework, an improved Actor-Critic structure is designed, and the policy and value network of the original structure are modified accordingly. We verify the success rate and time efficiency of different numbers of UAV group navigation in the urban environment. The experimental results show that this method can reduce the training convergence time and improve the efficiency and success rate of navigation. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Temporally Consistent 3D Human Motion Estimation from a Video 7

Temporally Consistent 3D Human Motion Estimation from a Vide...

引用

7th International Conference on Computer Graphics and Virtuality, ICCGV 2024

作者： Zhang, Zhaobing Liu, Yuehu Wang, Shaorong Yan, Yuanfeng School of Software Engineering Xi’an Jiaotong University Xi’an China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9781510679788

ISBN: (纸本)9781510679771

It is still difficult to accurately extract smooth and consistent 3D human motion from video footage over time. While some existing techniques have achieved favorable outcomes by utilizing the combined features of consecutive frames, many of them compromise accuracy in order to reduce jitter or do not have a complete understanding of the temporal nature of human movement. To this end, we model the natural smoothing properties in body motion by learning the long-range temporal relationship between the kinematic features of the human body in the video and the enhanced current frame features. First, we use the velocity and acceleration of key points to effectively capture temporal features as our temporal motion prior, and then we have created a module that uses a hierarchical attention mechanism to improve the representation of the current frame by selectively focusing on important temporal information from both past and future frames. This enhances the correlation between frames and improves the overall quality of the feature representation. Ultimately these two parts of features are aggregated together through a global motion aware network and linear fusion is performed to obtain the final accurate 3D human motion. © 2024 SPIE.

关键词： Acceleration

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：