2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第3页

Learning-Based Sampling for Natural Image Matting 基于学习的自然图像抠图采样

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00317

Jingwei Tang, Yagiz Aksoy, C. Öztireli, M. Gross, T. Aydin

{"title":"Learning-Based Sampling for Natural Image Matting","authors":"Jingwei Tang, Yagiz Aksoy, C. Öztireli, M. Gross, T. Aydin","doi":"10.1109/CVPR.2019.00317","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00317","url":null,"abstract":"The goal of natural image matting is the estimation of opacities of a user-defined foreground object that is essential in creating realistic composite imagery. Natural matting is a challenging process due to the high number of unknowns in the mathematical modeling of the problem, namely the opacities as well as the foreground and background layer colors, while the original image serves as the single observation. In this paper, we propose the estimation of the layer colors through the use of deep neural networks prior to the opacity estimation. The layer color estimation is a better match for the capabilities of neural networks, and the availability of these colors substantially increase the performance of opacity estimation due to the reduced number of unknowns in the compositing equation. A prominent approach to matting in parallel to ours is called sampling-based matting, which involves gathering color samples from known-opacity regions to predict the layer colors. Our approach outperforms not only the previous hand-crafted sampling algorithms, but also current data-driven methods. We hence classify our method as a hybrid sampling- and learning-based approach to matting, and demonstrate the effectiveness of our approach through detailed ablation studies using alternative network architectures.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"33 1","pages":"3050-3058"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85523362","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: 95

Inverse Procedural Modeling of Knitwear 针织品的逆过程建模

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00883

E. Trunz, S. Merzbach, Jonathan Klein, Thomas Schulze, Michael Weinmann, R. Klein

引用次数: 5

Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks 注意你的邻居:使用元数据邻居图共同关注网络的图像标注

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00307

Junjie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu

{"title":"Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks","authors":"Junjie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu","doi":"10.1109/CVPR.2019.00307","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00307","url":null,"abstract":"As the visual reflections of our daily lives, images are frequently shared on the social network, which generates the abundant 'metadata' that records user interactions with images. Due to the diverse contents and complex styles, some images can be challenging to recognise when neglecting the context. Images with the similar metadata, such as 'relevant topics and textual descriptions', 'common friends of users' and 'nearby locations', form a neighbourhood for each image, which can be used to assist the annotation. In this paper, we propose a Metadata Neighbourhood Graph Co-Attention Network (MangoNet) to model the correlations between each target image and its neighbours. To accurately capture the visual clues from the neighbourhood, a co-attention mechanism is introduced to embed the target image and its neighbours as graph nodes, while the graph edges capture the node pair correlations. By reasoning on the neighbourhood graph, we obtain the graph representation to help annotate the target image. Experimental results on three benchmark datasets indicate that our proposed model achieves the best performance compared to the state-of-the-art methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"2010 1","pages":"2951-2959"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73590977","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

Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking 消除多目标跟踪中的曝光偏差和度量不匹配

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00477

Andrii Maksai, P. Fua

引用次数: 54

Convolutional Recurrent Network for Road Boundary Extraction 基于卷积递归网络的道路边界提取

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00974

Justin Liang, N. Homayounfar, Wei-Chiu Ma, Shenlong Wang, R. Urtasun

引用次数: 60

Learning Unsupervised Video Object Segmentation Through Visual Attention 通过视觉注意学习无监督视频对象分割

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00318

Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen, Sanyuan Zhao, S. Hoi, Haibin Ling

{"title":"Learning Unsupervised Video Object Segmentation Through Visual Attention","authors":"Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen, Sanyuan Zhao, S. Hoi, Haibin Ling","doi":"10.1109/CVPR.2019.00318","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00318","url":null,"abstract":"This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects and SegTrack V2) with dynamic eye-tracking data in the UVOS setting, for the first time, we quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgements during dynamic, task-driven viewing. Such novel observations provide an in-depth insight into the underlying rationale behind UVOS. Inspired by these findings, we decouple UVOS into two sub-tasks: UVOS-driven Dynamic Visual Attention Prediction (DVAP) in spatiotemporal domain, and Attention-Guided Object Segmentation (AGOS) in spatial domain. Our UVOS solution enjoys three major merits: 1) modular training without using expensive video segmentation annotations, instead, using more affordable dynamic fixation data to train the initial video attention module and using existing fixation-segmentation paired static/image data to train the subsequent segmentation module; 2) comprehensive foreground understanding through multi-source learning; and 3) additional interpretability from the biologically-inspired and assessable attention. Experiments on popular benchmarks show that, even without using expensive video object mask annotations, our model achieves compelling performance in comparison with state-of-the-arts.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"40 1","pages":"3059-3069"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82207707","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: 176

Frame-Consistent Recurrent Video Deraining With Dual-Level Flow 基于双级流的帧一致循环视频训练

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00176

Wenhan Yang, Jiaying Liu, Jiashi Feng

{"title":"Frame-Consistent Recurrent Video Deraining With Dual-Level Flow","authors":"Wenhan Yang, Jiaying Liu, Jiashi Feng","doi":"10.1109/CVPR.2019.00176","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00176","url":null,"abstract":"In this paper, we address the problem of rain removal from videos by proposing a more comprehensive framework that considers the additional degradation factors in real scenes neglected in previous works. The proposed framework is built upon a two-stage recurrent network with dual-level flow regularizations to perform the inverse recovery process of the rain synthesis model for video deraining. The rain-free frame is estimated from the single rain frame at the first stage. It is then taken as guidance along with previously recovered clean frames to help obtain a more accurate clean frame at the second stage. This two-step architecture is capable of extracting more reliable motion information from the initially estimated rain-free frame at the first stage for better frame alignment and motion modeling at the second stage. Furthermore, to keep the motion consistency between frames that facilitates a frame-consistent deraining model at the second stage, a dual-level flow based regularization is proposed at both coarse flow and fine pixel levels. To better train and evaluate the proposed video deraining network, a novel rain synthesis model is developed to produce more visually authentic paired training and evaluation videos. Extensive experiments on a series of synthetic and real videos verify not only the superiority of the proposed method over state-of-the-art but also the effectiveness of network design and its each component.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"269 1","pages":"1661-1670"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76190182","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

Light Field Messaging With Deep Photographic Steganography 光场信息与深摄影隐写术

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00161

Eric Wengrowski, Kristin J. Dana

{"title":"Light Field Messaging With Deep Photographic Steganography","authors":"Eric Wengrowski, Kristin J. Dana","doi":"10.1109/CVPR.2019.00161","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00161","url":null,"abstract":"We develop Light Field Messaging (LFM), a process of embedding, transmitting, and receiving hidden information in video that is displayed on a screen and captured by a handheld camera. The goal of the system is to minimize perceived visual artifacts of the message embedding, while simultaneously maximizing the accuracy of message recovery on the camera side. LFM requires photographic steganography for embedding messages that can be displayed and camera-captured. Unlike digital steganography, the embedding requirements are significantly more challenging due to the combined effect of the screen's radiometric emittance function, the camera's sensitivity function, and the camera-display relative geometry. We devise and train a network to jointly learn a deep embedding and recovery algorithm that requires no multi-frame synchronization. A key novel component is the camera display transfer function (CDTF) to model the camera-display pipeline. To learn this CDTF we introduce a dataset (Camera-Display 1M) of 1,000,000 camera-captured images collected from 25 camera-display pairs. The result of this work is a high-performance real-time LFM system using consumer-grade displays and smartphone cameras.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"14 1","pages":"1515-1524"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87853336","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: 93

EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors ev -步态:基于事件的鲁棒动态视觉传感器步态识别

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00652

Yanxiang Wang, Bowen Du, Yiran Shen, Kai Wu, Guangrong Zhao, Jianguo Sun, Hongkai Wen

{"title":"EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors","authors":"Yanxiang Wang, Bowen Du, Yiran Shen, Kai Wu, Guangrong Zhao, Jianguo Sun, Hongkai Wen","doi":"10.1109/CVPR.2019.00652","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00652","url":null,"abstract":"In this paper, we introduce a new type of sensing modality, the Dynamic Vision Sensors (Event Cameras), for the task of gait recognition. Compared with the traditional RGB sensors, the event cameras have many unique advantages such as ultra low resources consumption, high temporal resolution and much larger dynamic range. However, those cameras only produce noisy and asynchronous events of intensity changes rather than frames, where conventional vision-based gait recognition algorithms can’t be directly applied. To address this, we propose a new Event-based Gait Recognition (EV-Gait) approach, which exploits motion consistency to effectively remove noise, and uses a deep neural network to recognise gait from the event streams. To evaluate the performance of EV-Gait, we collect two event-based gait datasets, one from real-world experiments and the other by converting the publicly available RGB gait recognition benchmark CASIA-B. Extensive experiments show that EV-Gait can get nearly 96% recognition accuracy in the real-world settings, while on the CASIA-B benchmark it achieves comparable performance with state-of-the-art RGB-based gait recognition approaches.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"14 1","pages":"6351-6360"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87577790","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: 88

AutoAugment: Learning Augmentation Strategies From Data 自动增强:从数据中学习增强策略

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00020

E. D. Cubuk, Barret Zoph, Dandelion Mané, Vijay Vasudevan, Quoc V. Le

{"title":"AutoAugment: Learning Augmentation Strategies From Data","authors":"E. D. Cubuk, Barret Zoph, Dandelion Mané, Vijay Vasudevan, Quoc V. Le","doi":"10.1109/CVPR.2019.00020","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00020","url":null,"abstract":"Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-the-art. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"7 1","pages":"113-123"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87603087","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: 1666