检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Mao, Mingyuan Tian, Yuxin Zhang, Baochang Ye, Qixiang Liu, Wanquan Guo, Guodong Doermann, David Beihang University Beijing China University of Chinese Academy of Sciences Beijing China Curtin University Perth Australia Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application University at Buffalo Buffalo United States

Modern CNN-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the IFF module performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. By applying Fourier transform analysis, we demonstrate that the IFF module acts as a negative feedback that theoretically guarantees the stability of feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods by significant margins1. Copyright © 2020, 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

FaceScape: A large-scale high quality 3D face dataset and detailed riggable 3D face prediction

arXiv

引用

arXiv 2020年

作者： Yang, Haotian Zhu, Hao Wang, Yanru Huang, Mingkai Shen, Qiu Yang, Ruigang Cao, Xun Nanjing University China Baidu Research University of Kentucky United States Inceptio Inc National Engineering Laboratory for Deep Learning Technology and Applications China

In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and propose a novel algorithm that is able to predict elaborate riggable 3D face models from a single image input. FaceScape dataset provides 18,760 textured 3D faces, captured from 938 subjects and each with 20 specific expressions. The 3D models contain the pore-level facial geometry that is also processed to be topologically uniformed. These fine 3D facial models can be represented as a 3D morphable model for rough shapes and displacement maps for detailed geometry. Taking advantage of the large-scale and high-accuracy dataset, a novel algorithm is further proposed to learn the expression-specific dynamic details using a deep neural network. The learned relationship serves as the foundation of our 3D face prediction system from a single image input. Different than the previous methods, our predicted 3D models are riggable with highly detailed geometry under different expressions. The unprecedented dataset and code will be released to public for research purpose†. Copyright © 2020, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Channel Attention Based Iterative Residual learning for Depth Map Super-Resolution

Channel Attention Based Iterative Residual Learning for Dept...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xibin Song Yuchao Dai Dingfu Zhou Liu Liu Wei Li Hongdong Li Ruigang Yang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China Northwestern Polytechnical University China Australian National University Australia Australian Centre for Robotic Vision Australia Shandong University China University of Kentucky Kentucky USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Despite the remarkable progresses made in deep learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and tested on synthetic dataset, which is very different from what would get from a real depth sensor. In this paper, we argue that DSR models trained under this setting are restrictive and not effective in dealing with realworld DSR tasks. We make two contributions in tackling real-world degradation of different depth sensors. First, we propose to classify the generation of LR depth maps into two types: non-linear downsampling with noise and interval downsampling, for which DSR models are learned correspondingly. Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively reexploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss. Extensive experiments on benchmarking datasets demonstrate the superiority of our method over current state-of-the-art DSR methods.

关键词： Degradation Iron Color Kernel Image resolution Three-dimensional displays Feature extraction

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer Attention

LiDAR-Based Online 3D Video Object Detection With Graph-Base...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junbo Yin Jianbing Shen Chenye Guan Dingfu Zhou Ruigang Yang Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China Baidu Research Inception Institute of Artificial Intelligence UAE National Engineering Laboratory of Deep Learning Technology and Application China University of Kentucky Kentucky USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences. The proposed model comprises a spatial feature encoding component and a spatiotemporal feature aggregation component. In the former component, a novel Pillar Message Passing Network (PMPNet) is proposed to encode each discrete point cloud frame. It adaptively collects information for a pillar node from its neighbors by iterative message passing, which effectively enlarges the receptive field of the pillar feature. In the latter component, we propose an Attentive Spatiotemporal Transformer GRU (AST-GRU) to aggregate the spatiotemporal information, which enhances the conventional ConvGRU with an attentive memory gating mechanism. AST-GRU contains a Spatial Transformer Attention (STA) module and a Temporal Transformer Attention (TTA) module, which can emphasize the foreground objects and align the dynamic objects, respectively. Experimental results demonstrate that the proposed 3D video object detector achieves state-of-the-art performance on the large-scale nuScenes benchmark.

关键词： Three-dimensional displays Feature extraction Spatiotemporal phenomena Detectors Object detection Encoding Message passing

来源：评论

学校读者我要写书评

暂无评论

Channel attention based iterative residual learning for depth map super-resolution

arXiv

引用

arXiv 2020年

作者： Song, Xibin Dai, Yuchao Zhou, Dingfu Liu, Liu Li, Wei Li, Hongdong Yang, Ruigang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China Northwestern Polytechnical University China Shandong University China Australian National University Australia Australian Centre for Robotic Vision Australia University of Kentucky Kentucky United States

Despite the remarkable progresses made in deep-learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and tested on synthetic dataset, which is very different from what would get from a real depth sensor. In this paper, we argue that DSR models trained under this setting are restrictive and not effective in dealing with real-world DSR tasks. We make two contributions in tackling real-world degradation of different depth sensors. First, we propose to classify the generation of LR depth maps into two types: non-linear downsampling with noise and interval downsampling, for which DSR models are learned correspondingly. Second, we propose a new framework for real-world DSR, which consists of four modules: 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner;2) A channel attention strategy to enhance channels with abundant high-frequency components;3) A multi-stage fusion module to effectively re-exploit the results in the coarse-to-fine process;and 4) A depth refinement module to improve the depth map by TGV regularization and input loss. Extensive experiments on benchmarking datasets demonstrate the superiority of our method over current state-of-the-art DSR methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

A Unified Object Motion and Affinity Model for Online Multi-Object Tracking

A Unified Object Motion and Affinity Model for Online Multi-...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junbo Yin Wenguan Wang Qinghao Meng Ruigang Yang Jianbing Shen Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China ETH Zurich Switzerland Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China University of Kentucky Kentucky USA Inception Institute of Artificial Intelligence UAE

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.

关键词： Computational modeling Task analysis Target tracking Feature extraction Training

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention

arXiv

引用

arXiv 2020年

作者： Yin, Junbo Shen, Jianbing Guan, Chenye Zhou, Dingfu Yang, Ruigang Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China Inception Institute of Artificial Intelligence United Arab Emirates University of Kentucky Kentucky United States

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Joint 3D Instance Segmentation and Object Detection for Autonomous Driving

Joint 3D Instance Segmentation and Object Detection for Auto...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Dingfu Zhou Jin Fang Xibin Song Liu Liu Junbo Yin Yuchao Dai Hongdong Li Ruigang Yang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application Beijing China Australian National University Canberra Australia Australian Centre for Robotic Vision Australia Beijing Institute of Technology Beijing China Northwestern Polytechnical University Xi'an China University of Kentucky Kentucky USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Currently, in Autonomous Driving (AD), most of the 3D object detection frameworks (either anchor- or anchor-free-based) consider the detection as a Bounding Box (BBox) regression problem. However, this compact representation is not sufficient to explore all the information of the objects. To tackle this problem, we propose a simple but practical detection framework to jointly predict the 3D BBox and instance segmentation. For instance segmentation, we propose a Spatial Embeddings (SEs) strategy to assemble all foreground points into their corresponding object centers. Base on the SE results, the object proposals can be generated based on a simple clustering strategy. For each cluster, only one proposal is generated. Therefore, the Non-Maximum Suppression (NMS) process is no longer needed here. Finally, with our proposed instance-aware ROI pooling, the BBox is refined by a second-stage network. Experimental results on the public KITTI dataset show that the proposed SEs can significantly improve the instance segmentation results compared with other feature embedding-based method. Meanwhile, it also outperforms most of the 3D object detectors on the KITTI testing benchmark.

关键词： Three-dimensional displays Object detection Two dimensional displays Proposals Feature extraction Shape Semantics

来源：评论

学校读者我要写书评

暂无评论

Knowledge Abstraction Matching for Medical Question Answering

Knowledge Abstraction Matching for Medical Question Answerin...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jun Chen Jingbo Zhou Zhenhui Shi Bin Fan Chengliang Luo Baidu Inc Beijing China Business Intelligence Lab Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China

Medical Question Answering (medical QA), which studies the problem of automatically answering patients' medical questions online, is one of the major applications of bioinformatics. Though many efforts have been made before, the medical QA system still deserves delicate algorithm optimization due to the serious application scenario and strict requirement for the answer quality. In this paper, we introduce a novel Knowledge Abstraction Matching (KAM) method for the medical QA problem. The intuition of KAM is that there are many frequent repeat text segments appearing in the answers across different questions. From this view, we propose a new method that consists of frequent segment N-gram mining, medical knowledge abstraction, medical segment matching and answer re-retrieval. KAM has been incorporated into baidu's enterprise medical QA system MelodyQA deployed on the backend of Muzhi Doctor. The evaluation shows that the proposed method can generate more quality answers for MelodyQA with a significant improvement of question coverage under acceptable accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

$\mathsf{NCF}$NCF: A Neural Context Fusion Approach to Raw Mobility Annotation

引用

IEEE Transactions on Mobile Computing 2020年第1期21卷 226-238页

作者： Renjun Hu Jingbo Zhou Xinjiang Lu Hengshu Zhu Shuai Ma Hui Xiong SKLSDE Lab Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Business Intelligence Lab Baidu Research National Engineering Laboratory of Deep Learning Technology and Application Beijing China Talent Intelligence Center Baidu Inc. Beijing China Management Science and Information Systems Department Rutgers Business School Rutgers University Newark NJ USA

Understanding human mobility patterns at the point-of-interest (POI) scale plays an important role in enhancing business intelligence in mobile environments. While large efforts have been made in this direction, most studies simply utilize POI check-ins to mine the concerned mobility patterns, the effectiveness of which is usually hindered due to data sparsity. To obtain better POI-based human mobility for mining, in this paper, we strive to directly annotate the POIs associated with raw user-generated mobility records. We propose a neural context fusion approach which integrates various context factors in people's POI-visiting behaviors. Our approach evaluates the preference and transition factors via representation learning. Notably, we incorporate an attention mechanism to deal with the randomized transitions in raw mobility. The domain knowledge factors, i.e., distance, time and popularity, remain effective and our approach further includes them from a data-driven perspective. Factors are automatically fused with a feed-forward neural network. Furthermore, we exploit a multi-head architecture to enhance the model expressiveness. Using two real-life data sets, we conduct our experimental study and find that our approach consistently outperforms the state-of-the-art baselines by at least 32 percent in accuracy. Besides, we demonstrate the utility of the obtained POI-based human mobility with a POI recommendation example.

关键词： Annotations Trajectory Mobile computing Computer architecture Business intelligence Neural networks Semantics

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：