2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第9页

Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition 球面分形卷积神经网络在点云识别中的应用

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00054

Yongming Rao, Jiwen Lu, Jie Zhou

引用次数: 122

Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation 上下文感知的空间循环曲线结构分割

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01293

Feigege Wang, Yue Gu, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jianxiong Pan

{"title":"Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation","authors":"Feigege Wang, Yue Gu, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jianxiong Pan","doi":"10.1109/CVPR.2019.01293","DOIUrl":"https://doi.org/10.1109/CVPR.2019.01293","url":null,"abstract":"Curvilinear structures are frequently observed in various images in different forms, such as blood vessels or neuronal boundaries in biomedical images. In this paper, we propose a novel curvilinear structure segmentation approach using context-aware spatio-recurrent networks. Instead of directly segmenting the whole image or densely segmenting fixed-sized local patches, our method recurrently samples patches with varied scales from the target image with learned policy and processes them locally, which is similar to the behavior of changing retinal fixations in the human visual system and it is beneficial for capturing the multi-scale or hierarchical modality of the complex curvilinear structures. In specific, the policy of choosing local patches is attentively learned based on the contextual information of the image and the historical sampling experience. In this way, with more patches sampled and refined, the segmentation of the whole image can be progressively improved. To validate our approach, comparison experiments on different types of image data are conducted and the sampling procedures for exemplar images are illustrated. We demonstrate that our method achieves the state-of-the-art performance in public datasets.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"62 1","pages":"12640-12649"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84292117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 14

Acoustic Non-Line-Of-Sight Imaging 声学非视距成像

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00694

David B. Lindell, Gordon Wetzstein, V. Koltun

引用次数: 74

Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions 道路规则:用语义交互的卷积模型预测驾驶行为

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00865

Joey Hong, Benjamin Sapp, James Philbin

{"title":"Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions","authors":"Joey Hong, Benjamin Sapp, James Philbin","doi":"10.1109/CVPR.2019.00865","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00865","url":null,"abstract":"We focus on the problem of predicting future states of entities in complex, real-world driving scenarios. Previous research has approached this problem via low-level signals to predict short time horizons, and has not addressed how to leverage key assets relied upon heavily by industry self-driving systems: (1) large 3D perception efforts which provide highly accurate 3D states of agents with rich attributes, and (2) detailed and accurate semantic maps of the environment (lanes, traffic lights, crosswalks, etc). We present a unified representation which encodes such high-level semantic information in a spatial grid, allowing the use of deep convolutional models to fuse complex scene context. This enables learning entity-entity and entity-environment interactions with simple, feed-forward computations in each timestep within an overall temporal model of an agent's behavior. We propose different ways of modelling the future as a {em distribution} over future states using standard supervised learning. We introduce a novel dataset providing industry-grade rich perception and semantic inputs, and empirically show we can effectively learn fundamentals of driving behavior.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"8446-8454"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86856795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 195

Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution 在时间分布中使用分数各向异性的野生视频放大

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00171

Shoichiro Takeda, Yasunori Akagi, Kazuki Okami, M. Isogai, H. Kimata

{"title":"Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution","authors":"Shoichiro Takeda, Yasunori Akagi, Kazuki Okami, M. Isogai, H. Kimata","doi":"10.1109/CVPR.2019.00171","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00171","url":null,"abstract":"Video magnification methods can magnify and reveal subtle changes invisible to the naked eye. However, in such subtle changes, meaningful ones caused by physical and natural phenomena are mixed with non-meaningful ones caused by photographic noise. Therefore, current methods often produce noisy and misleading magnification outputs due to the non-meaningful subtle changes. For detecting only meaningful subtle changes, several methods have been proposed but require human manipulations, additional resources, or input video scene limitations. In this paper, we present a novel method using fractional anisotropy (FA) to detect only meaningful subtle changes without the aforementioned requirements. FA has been used in neuroscience to evaluate anisotropic diffusion of water molecules in the body. On the basis of our observation that temporal distribution of meaningful subtle changes more clearly indicates anisotropic diffusion than that of non-meaningful ones, we used FA to design a fractional anisotropic filter that passes only meaningful subtle changes. Using the filter enables our method to obtain better and more impressive magnification results than those obtained with state-of-the-art methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"22 1","pages":"1614-1622"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85775420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification 基于度量融合的目标检索和人物再识别排序

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00083

S. Bai, Peng Tang, Philip H. S. Torr, Longin Jan Latecki

{"title":"Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification","authors":"S. Bai, Peng Tang, Philip H. S. Torr, Longin Jan Latecki","doi":"10.1109/CVPR.2019.00083","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00083","url":null,"abstract":"This work studies the unsupervised re-ranking procedure for object retrieval and person re-identification with a specific concentration on an ensemble of multiple metrics (or similarities). While the re-ranking step is involved by running a diffusion process on the underlying data manifolds, the fusion step can leverage the complementarity of multiple metrics. We give a comprehensive summary of existing fusion with diffusion strategies, and systematically analyze their pros and cons. Based on the analysis, we propose a unified yet robust algorithm which inherits their advantages and discards their disadvantages. Hence, we call it Unified Ensemble Diffusion (UED). More interestingly, we derive that the inherited properties indeed stem from a theoretical framework, where the relevant works can be elegantly summarized as special cases of UED by imposing additional constraints on the objective function and varying the solver of similarity propagation. Extensive experiments with 3D shape retrieval, image retrieval and person re-identification demonstrate that the proposed framework outperforms the state of the arts, and at the same time suggest that re-ranking via metric fusion is a promising tool to further improve the retrieval performance of existing algorithms.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"73 1","pages":"740-749"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86352676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 80

DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios driingstereo:用于自动驾驶场景立体匹配的大规模数据集

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00099

Guorun Yang, Xiao Song, Chaoqin Huang, Zhidong Deng, Jianping Shi, Bolei Zhou

{"title":"DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios","authors":"Guorun Yang, Xiao Song, Chaoqin Huang, Zhidong Deng, Jianping Shi, Bolei Zhou","doi":"10.1109/CVPR.2019.00099","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00099","url":null,"abstract":"Great progress has been made on estimating disparity maps from stereo images. However, with the limited stereo data available in the existing datasets and unstable ranging precision of current stereo methods, industry-level stereo matching in autonomous driving remains challenging. In this paper, we construct a novel large-scale stereo dataset named DrivingStereo. It contains over 180k images covering a diverse set of driving scenarios, which is hundreds of times larger than the KITTI Stereo dataset. High-quality labels of disparity are produced by a model-guided filtering strategy from multi-frame LiDAR points. For better evaluations, we present two new metrics for stereo matching in the driving scenes, i.e. a distance-aware metric and a semantic-aware metric. Extensive experiments show that compared with the models trained on FlyingThings3D or Cityscapes, the models trained on our DrivingStereo achieve higher generalization accuracy in real-world driving scenes, while the proposed metrics better evaluate the stereo methods on all-range distances and across different classes. Our dataset and code are available at https://drivingstereo-dataset.github.io.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"34 1","pages":"899-908"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85554546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 112

Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation 远距离监督质心移位:一种简单有效的视觉域自适应方法

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00309

Jian Liang, R. He, Zhenan Sun, T. Tan

{"title":"Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation","authors":"Jian Liang, R. He, Zhenan Sun, T. Tan","doi":"10.1109/CVPR.2019.00309","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00309","url":null,"abstract":"Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains. However, most deep learning methods highly rely on large-size source domains and are computationally expensive to train, while subspace learning methods always have a quadratic time complexity that suffers from the large domain size. This paper provides a simple and efficient solution, which could be regarded as a well-performing baseline for domain adaptation tasks. Our method is built upon the nearest centroid classifier, seeking a subspace where the centroids in the target domain are moderately shifted from those in the source domain. Specifically, we design a unified objective without accessing the source domain data and adopt an alternating minimization scheme to iteratively discover the pseudo target labels, invariant subspace, and target centroids. Besides its privacy-preserving property (distant supervision), the algorithm is provably convergent and has a promising linear time complexity. In addition, the proposed method can be readily extended to multi-source setting and domain generalization, and it remarkably enhances popular deep adaptation methods by borrowing the learned transferable features. Extensive experiments on several benchmarks including object, digit, and face recognition datasets validate that our methods yield state-of-the-art results in various domain adaptation tasks.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"24 1","pages":"2970-2979"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73073990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 76

Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing 基于多尺度标签平滑的掩模引导全卷积网络的协显著性检测

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00321

Kaihua Zhang, Tengpeng Li, Bo Liu, Qingshan Liu

引用次数: 70

Robustness Verification of Classification Deep Neural Networks via Linear Programming 基于线性规划的分类深度神经网络鲁棒性验证

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01168

Wang Lin, Zhengfeng Yang, Xin Chen, Qingye Zhao, Xiangkun Li, Zhiming Liu, Jifeng He

引用次数: 34