2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition最新文献_第8页

Modeling Facial Geometry Using Compositional VAEs 使用合成VAEs建模面部几何

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00408

Timur M. Bagautdinov, Chenglei Wu, Jason M. Saragih, P. Fua, Yaser Sheikh

引用次数: 93

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation 无显式运动补偿的动态上采样滤波器深度视频超分辨率网络

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00340

Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, Seon Joo Kim

引用次数: 439

Occlusion-Aware Rolling Shutter Rectification of 3D Scenes 三维场景的闭塞感知卷帘门校正

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00073

Subeesh Vasu, R. MaheshMohanM., A. Rajagopalan

引用次数: 33

Egocentric Activity Recognition on a Budget 预算中的自我中心活动识别

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00625

Rafael Possas, Sheila M. Pinto-Caceres, F. Ramos

引用次数: 37

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials RayNet:学习用射线势进行体积三维重建

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00410

Despoina Paschalidou, Ali O. Ulusoy, Carolin Schmitt, L. Gool, Andreas Geiger

引用次数: 77

PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos PoseFlow:用于理解视频中人类行为的深度运动表示

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00707

Dingwen Zhang, Guangyu Guo, Dong Huang, Junwei Han

引用次数: 31

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks 低比特深度神经网络的显式损失误差感知量化

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00982

Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen

{"title":"Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks","authors":"Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen","doi":"10.1109/CVPR.2018.00982","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00982","url":null,"abstract":"Benefiting from tens of millions of hierarchically stacked learnable parameters, Deep Neural Networks (DNNs) have demonstrated overwhelming accuracy on a variety of artificial intelligence tasks. However reversely, the large size of DNN models lays a heavy burden on storage, computation and power consumption, which prohibits their deployments on the embedded and mobile systems. In this paper, we propose Explicit Loss-error-aware Quantization (ELQ), a new method that can train DNN models with very low-bit parameter values such as ternary and binary ones to approximate 32-bit floating-point counterparts without noticeable loss of predication accuracy. Unlike existing methods that usually pose the problem as a straightforward approximation of the layer-wise weights or outputs of the original full-precision model (specifically, minimizing the error of the layer-wise weights or inner products of the weights and the inputs between the original and respective quantized models), our ELQ elaborately bridges the loss perturbation from the weight quantization and an incremental quantization strategy to address DNN quantization. Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective. As validated with two mainstream convolutional neural network families (i.e., fully convolutional and non-fully convolutional), our ELQ shows better results than state-of-the-art quantization methods on the large scale ImageNet classification dataset. Code will be made publicly available.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88204691","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

SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation 基于对抗性正面实例生成的稳健视觉跟踪

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00511

Xiao Wang, Chenglong Li, B. Luo, Jin Tang

{"title":"SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation","authors":"Xiao Wang, Chenglong Li, B. Luo, Jin Tang","doi":"10.1109/CVPR.2018.00511","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00511","url":null,"abstract":"Existing visual trackers are easily disturbed by occlusion, blur and large deformation. We think the performance of existing visual trackers may be limited due to the following issues: i) Adopting the dense sampling strategy to generate positive examples will make them less diverse; ii) The training data with different challenging factors are limited, even through collecting large training dataset. Collecting even larger training dataset is the most intuitive paradigm, but it may still can not cover all situations and the positive samples are still monotonous. In this paper, we propose to generate hard positive samples via adversarial learning for visual tracking. Specifically speaking, we assume the target objects all lie on a manifold, hence, we introduce the positive samples generation network (PSGN) to sampling massive diverse training data through traversing over the constructed target object manifold. The generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. To make the tracker more robust to occlusion, we adopt the hard positive transformation network (HPTN) which can generate hard samples for tracking algorithm to recognize. We train this network with deep reinforcement learning to automatically occlude the target object with a negative patch. Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm. The project page of this paper can be found from the website1.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85314580","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: 109

SSNet: Scale Selection Network for Online 3D Action Prediction SSNet:用于在线三维动作预测的尺度选择网络

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00871

Jun Liu, Amir Shahroudy, G. Wang, Ling-yu Duan, A. Kot

引用次数: 54

A Revised Underwater Image Formation Model 一种改进的水下图像形成模型

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 DOI: 10.1109/CVPR.2018.00703

D. Akkaynak, T. Treibitz

引用次数: 172