检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Real-Time Computing and robotics, RCAR 2019

作者： Zhang, Weitong Tian, Yanling Zhang, Qieshi Cheng, Jun Zheng, Huiquan Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Chinese University of Hong Kong Hong Kong Hong Kong School of Computer Science Shaanxi Normal University Xi'an China

ISBN: (数字)9781728137261

ISBN: (纸本)9781728137261

One of the major challenges in object recognition is to propose a structure with highly performance of overlapping, small and misclassification objects, called hard object recognition. There is a contextual nexus among the spatial location and geometric characteristics of objects, which we find is essential to the recognition efficacy. We propose regress connection, nexus calculation module and linkage loss, which are contained in an improving design TransNet framework. It can not only demonstrates the interactivity of explicit nexus between objects, but also achieve better results through the integration of two mainstream methods. Adjusting the training attention through linkage loss function, thus significantly enhance the performance of hard objects. The experiment results show that our method achieves remarkable performance on PASCAL VOC2012 and MS COCO data set. Also, the head network is capable of integrating with region-based methods and gains better performance. © 2019 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A novel skeleton-based action recognition method via cuboid rearranging

A novel skeleton-based action recognition method via cuboid ...

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Zhu, Kaijun Wang, Ruxin Cheng, Jun Tao, Dapeng FIST LAB Yunnan University Kunming Yunnan650091 China Shenzhen Union Vision Innovation Technology Co Ltd. China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences Shenzhen518055 China Chinese University of Hong Kong Hong Kong999077 Hong Kong

ISBN: (纸本)9781538680698

Depth sensors such as Microsoft Kinect v2 have promoted the active research of human action recognition in recent years. While a great progress has been witnessed, most of existing skeleton-based approaches neglect the fact that only parts of the human body move in an action, and they fail to consider the ordinal positions of the body joints. In this paper, we are motivated by the fact that the category of an action is determined by local movements of body joints, and propose an attended cuboid model for skeleton-based action recognition. Specifically, a cuboid arranging strategy is developed to organize the pairwise displacement vectors among all body joints, where a cuboid representation of actions is obtained. Such a representation is well structured and allows the deep CNN models to analyze an action in a concentrated way. Moreover, an attention mechanism is exploited in the deep model, such that the most relevant features can be extracted. Extensive experiments on three popular datasets demonstrate the effectiveness of our method compared with the state-of-the-arts. © 2018 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

A single 2D pose with context is worth hundreds for 3D human pose estimation 23

A single 2D pose with context is worth hundreds for 3D human...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qitao Zhao Ce Zheng Mengyuan Liu Chen Chen Robotics Institute Carnegie Mellon University Center for Research in Computer Vision University of Central Florida Key Laboratory of Machine Perception Peking University Shenzhen Graduate School

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [74], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADATS: Adaptive RoI-Align based Transformer for End-to-End Text Spotting

ADATS: Adaptive RoI-Align based Transformer for End-to-End T...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zepeng Huang Qi Wan Junliang Chen Xiaodong Zhao Kai Ye Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Scene text spotting has attracted great attention in recent years. Compared with two-stage approaches that locate scene texts in the first stage and recognize them in the second stage, the advantages of joint location and recognition training are not fully explored. In this paper, we present an ADaptive RoI-Align based transformer for end-to-end Text Spotting (ADATS), which simultaneously locates and recognizes text with a single forward pass. By employing an Adaptive RoI-Align, the text features are extracted from the feature extraction network with the original aspect ratio, such that less information is lost during the alignment of arbitrarily-shaped scene text. Attention-based segmentation and recognition heads allow us to simultaneously optimize detection and recognition. Experiments on ICDAR 2015, MSRA-TD500, Total-Text, and CTW1500 demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-guided Representation Learning for Underwater Object Detection

arXiv

引用

arXiv 2023年

作者： Dai, Linhui Liu, Hong Song, Pinhao Tang, Hao Ding, Runwei Li, Shengquan Key Laboratory of Machine Perception Shenzhen Graduate School Peking University Shenzhen China Robotics Research Group KU Leuven Leuven Belgium Computer Vision Lab ETH Zurich Zurich Switzerland Peng Cheng Laboratory Shenzhen China

Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet’s sustainable development. The main challenges of this task arise from low-contrast, small objects, and mimicry of aquatic organisms. The key to addressing these challenges is to focus the model on obtaining more discriminative information. We observe that the edges of underwater objects are highly unique and can be distinguished from low-contrast or mimicry environments based on their edges. Motivated by this observation, we propose an Edge-guided Representation Learning Network, termed ERL-Net, that aims to achieve discriminative representation learning and aggregation under the guidance of edge cues. Firstly, we introduce an edge-guided attention module to model the explicit boundary information, which generates more discriminative features. Secondly, a feature aggregation module is proposed to aggregate the multi-scale discriminative features by regrouping them into three levels, effectively aggregating global and local information for locating and recognizing underwater objects. Finally, we propose a wide and asymmetric receptive field block to enable features to have a wider receptive field, allowing the model to focus on more small object information. Comprehensive experiments on three challenging underwater datasets show that our method achieves superior performance on the UOD task. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition

arXiv

引用

arXiv 2022年

作者： Luo, Cheng Song, Siyang Xie, Weicheng Shen, Linlin Gunes, Hatice Computer Vision Institute Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China Department of Computer Science and Technology University of Cambridge United Kingdom

The activations of Facial Action Units (AUs) mutually influence one another. While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display. This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. Our approach first encodes each AU’s activation status and its association with other AUs into a node feature. Then, it learns a pair of multi-dimensional edge features to describe multiple task-specific relationship cues between each pair of AUs. During both node and edge feature learning, our approach also considers the influence of the unique facial display on AUs’ relationship by taking the full face representation as an input. Experimental results on BP4D and DISFA datasets show that both node and edge feature learning modules provide large performance improvements for CNN and transformer-based backbones, with our best systems achieving the state-of-the-art AU recognition results. Our approach not only has a strong capability in modelling relationship cues for AU recognition but also can be easily incorporated into various backbones. Our PyTorch code is made available at https://***/CVI-SZU/ME-GraphAU. Copyright © 2022, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Group-wise Inhibition based Feature Regularization for Robust Classification

Group-wise Inhibition based Feature Regularization for Robus...

引用

International Conference on computer vision (ICCV)

作者： Haozhe Liu Haoqian Wu Weicheng Xie Feng Liu Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://***/LinusWu/TENET_Training.

关键词： Training computer vision Codes Heuristic algorithms Robustness Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Human Orientation Estimation Under Partial Observation

Human Orientation Estimation Under Partial Observation

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jieting Zhao Hanjing Ye Yu Zhan Hao Luan Hong Zhang Department of Electronic and Electrical Engineering SUSTech Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology (SUSTech) Department of Computer Science School of Computing National University of Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under full observation. However, the existing methods easily make a wrong prediction under partial observation and give it an unexpectedly high confidence. To solve the above problems, this study first develops a method called Part-HOE that estimates orientation from the visible joints of a target person so that it is able to handle partial observation. Subsequently, we introduce a confidence-aware orientation estimation method, enabling more accurate orientation estimation and reasonable confidence estimation under partial observation. The effectiveness of our method is validated on both public and custom-built datasets, and it shows great accuracy and reliability improvement in partial observation scenarios. In particular, we show in real experiments that our method can benefit the robustness and consistency of the Robot Person Following (RPF) task.

关键词： Accuracy Filtering Estimation Robustness Autonomous agents Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Hand gesture tracking and recognition based human-computer interaction system and its applications

Hand gesture tracking and recognition based human-computer i...

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Li, Kai Cheng, Jun Zhang, Qieshi Liu, Jianming School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Chinese Academy of Sciences Shenzhen China Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9781538680698

In this paper, we propose a human-computer interaction (HCI) system for entertainment or education via a depth-sensing camera. The whole system is comprised of three modules: hand detection, hand tracking, and gesture recognition. In our system, specifically, hand detection is based entirely on computer vision and do not use any markers. We utilize the Kalman filter and depth data from the Kinect to predict the hand position making the tracking smooth and robust. And we extract the apparent gestural features to recognize gestures, which are adaptable and quick. Two applications are in place to demonstrate the system: writing board, in which the user can freely draw lines in the air using their hand, and a classic game, Gluttonous snake, which is transformed into a novel game by using our framework. The system we develop is highly extendible and can be used in a wide variety of other interactive scenarios. © 2018 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

UDC-UNet: Under-Display Camera Image Restoration via U-shape Dynamic Network 17th

UDC-UNet: Under-Display Camera Image Restoration via U-shap...

引用

17th European Conference on computer vision, ECCV 2022

作者： Liu, Xina Hu, Jinfan Chen, Xiangyu Dong, Chao Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China University of Macau Zhuhai China Shanghai AI Laboratory Shanghai China

ISBN: (纸本)9783031250712

Under-Display Camera (UDC) has been widely exploited to help smartphones realize full-screen displays. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blur, and noise. Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes. In this paper, we propose a new deep model, namely UDC-UNet, to address the UDC image restoration problem with an estimated PSF in HDR scenes. Our network consists of three parts, including a U-shape base network to utilize multi-scale information, a condition branch to perform spatially variant modulation, and a kernel branch to leverage the prior knowledge of the PSF. According to the characteristics of HDR data, we additionally design a tone mapping loss to stabilize network optimization and achieve better visual quality. Experimental results show that the proposed UDC-UNet outperforms the state-of-the-art methods in quantitative and qualitative comparisons. Our approach won second place in the UDC image restoration track of the MIPI challenge. Codes and models are available at https://***/J-FHu/UDCUNet. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image reconstruction

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：