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

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

Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples 对抗实例的检索-增强卷积神经网络

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01183

Jake Zhao, Kyunghyun Cho

引用次数: 10

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks Occlusion-Net:使用图网络进行2D/3D遮挡关键点定位

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00750

Dinesh Reddy Narapureddy, Minh Vo, S. Narasimhan

{"title":"Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks","authors":"Dinesh Reddy Narapureddy, Minh Vo, S. Narasimhan","doi":"10.1109/CVPR.2019.00750","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00750","url":null,"abstract":"We present Occlusion-Net, a framework to predict 2D and 3D locations of occluded keypoints for objects, in a largely self-supervised manner. We use an off-the-shelf detector as input (like MaskRCNN) that is trained only on visible key point annotations. This is the only supervision used in this work. A graph encoder network then explicitly classifies invisible edges and a graph decoder network corrects the occluded keypoint locations from the initial detector. Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object. The 2D keypoints are then passed into a 3D graph network that estimates the 3D shape and camera pose using the self-supervised re-projection loss. At test time, our approach successfully localizes keypoints in a single view under a diverse set of severe occlusion settings. We demonstrate and evaluate our approach on synthetic CAD data as well as a large image set capturing vehicles at many busy city intersections. As an interesting aside, we compare the accuracy of human labels of invisible keypoints against those obtained from geometric trifocal-tensor loss.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"48 1","pages":"7318-7327"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74325584","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: 42

Dynamic Recursive Neural Network 动态递归神经网络

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00529

Qiushan Guo, Zhipeng Yu, Yichao Wu, Ding Liang, Haoyu Qin, Junjie Yan

引用次数: 41

Learning Linear Transformations for Fast Image and Video Style Transfer 学习线性变换快速图像和视频风格转移

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00393

Xueting Li, Sifei Liu, J. Kautz, Ming-Hsuan Yang

引用次数: 178

Learning Personalized Modular Network Guided by Structured Knowledge 结构化知识引导下的个性化模块化网络学习

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00915

Xiaodan Liang

{"title":"Learning Personalized Modular Network Guided by Structured Knowledge","authors":"Xiaodan Liang","doi":"10.1109/CVPR.2019.00915","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00915","url":null,"abstract":"The dominant deep learning approaches use a \"one-size-fits-all\" paradigm with the hope that underlying characteristics of diverse inputs can be captured via a fixed structure. They also overlook the importance of explicitly modeling feature hierarchy. However, complex real-world tasks often require discovering diverse reasoning paths for different inputs to achieve satisfying predictions, especially for challenging large-scale recognition tasks with complex label relations. In this paper, we treat the structured commonsense knowledge (e.g. concept hierarchy) as the guidance of customizing more powerful and explainable network structures for distinct inputs, leading to dynamic and individualized inference paths. Give an off-the-shelf large network configuration, the proposed Personalized Modular Network (PMN) is learned by selectively activating a sequence of network modules where each of them is designated to recognize particular levels of structured knowledge. Learning semantic configurations and activation of modules to align well with structured knowledge can be regarded as a decision-making procedure, which is solved by a new graph-based reinforcement learning algorithm. Experiments on three semantic segmentation tasks and classification tasks show our PMN can achieve superior performance with the reduced number of network modules while discovering personalized and explainable module configurations for each input.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"131 1","pages":"8936-8944"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76377204","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: 2

Sensitive-Sample Fingerprinting of Deep Neural Networks 深度神经网络的敏感样本指纹识别

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00486

Zecheng He, Tianwei Zhang, R. Lee

引用次数: 45

CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency CrDoCo:具有跨域一致性的像素级域传输

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00189

Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang

引用次数: 244

Adaptive Transfer Network for Cross-Domain Person Re-Identification 跨域人员再识别的自适应转移网络

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00737

Jiawei Liu, Zhengjun Zha, Di Chen, Richang Hong, Meng Wang

{"title":"Adaptive Transfer Network for Cross-Domain Person Re-Identification","authors":"Jiawei Liu, Zhengjun Zha, Di Chen, Richang Hong, Meng Wang","doi":"10.1109/CVPR.2019.00737","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00737","url":null,"abstract":"Recent deep learning based person re-identification approaches have steadily improved the performance for benchmarks, however they often fail to generalize well from one domain to another. In this work, we propose a novel adaptive transfer network (ATNet) for effective cross-domain person re-identification. ATNet looks into the essential causes of domain gap and addresses it following the principle of \"divide-and-conquer\". It decomposes the complicated cross-domain transfer into a set of factor-wise sub-transfers, each of which concentrates on style transfer with respect to a certain imaging factor, e.g., illumination, resolution and camera view etc. An adaptive ensemble strategy is proposed to fuse factor-wise transfers by perceiving the affect magnitudes of various factors on images. Such \"decomposition-and-ensemble\" strategy gives ATNet the capability of precise style transfer at factor level and eventually effective transfer across domains. In particular, ATNet consists of a transfer network composed by multiple factor-wise CycleGANs and an ensemble CycleGAN as well as a selection network that infers the affects of different factors on transferring each image. Extensive experimental results on three widely-used datasets, i.e., Market-1501, DukeMTMC-reID and PRID2011 have demonstrated the effectiveness of the proposed ATNet with significant performance improvements over state-of-the-art methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"57 1","pages":"7195-7204"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82802948","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: 217

Dichromatic Model Based Temporal Color Constancy for AC Light Sources 基于二色模型的交流光源时间色常数

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01261

Jun-Sang Yoo, Jong-Ok Kim

引用次数: 12