Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XVIVittorio Ferrari, Martial Hebert, Cristian Sminchisescu, Yair Weiss Springer, 2018 M10 6 - 871 pages The sixteen-volume set comprising the LNCS volumes 11205-11220 constitutes the refereed proceedings of the 15th European Conference on Computer Vision, ECCV 2018, held in Munich, Germany, in September 2018.The 776 revised papers presented were carefully reviewed and selected from 2439 submissions. The papers are organized in topical sections on learning for vision; computational photography; human analysis; human sensing; stereo and reconstruction; optimization; matching and recognition; video attention; and poster sessions. |
Contents
3 | |
21 | |
38 | |
Improving Deep Visual Representation for Person Reidentification by Global and Local Imagelanguage Association | 56 |
Learning 3D Shapes as Multilayered HeightMaps Using 2D Convolutional Networks | 74 |
A Geometric Perspective on Structured Light Coding | 90 |
Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network | 108 |
Selfsupervised Feature Learning by Lifting Views to Viewgrids | 126 |
Recognition in Terra Incognita | 472 |
A Minimal ClosedForm Solution for Multiperspective Pose Estimation using Points and Lines | 490 |
Lower Running Time and Higher Recall in Multicodebook Quantization | 508 |
On Regularized Losses for Weaklysupervised CNN Segmentation | 524 |
Dense Semantic and Topological Correspondence of 3D Faces without Landmarks | 541 |
Using Object Information for Spotting Text | 559 |
Remote Photoplethysmography Correspondence Feature for 3D Mask Face Presentation Attack Detection | 577 |
Hierarchical Bilinear Pooling for FineGrained Visual Recognition | 595 |
SuperResolution and Sparse View CT Reconstruction | 145 |
WeaklySupervised Temporal Action Localization in Untrimmed Videos | 162 |
Exploiting Vector Fields for Geometric Rectification of Distorted Document Images | 180 |
HardAware PointtoSet Deep Metric for Person Reidentification | 196 |
Image Generation from Sketch Constraint Using Contextual GAN | 213 |
Multiclass Model Fitting by Energy Minimization and ModeSeeking | 229 |
Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision | 246 |
A Unified Framework for Multiview Multiclass Object Pose Estimation | 263 |
Dynamic Task Prioritization for Multitask Learning | 282 |
Joint Blind Motion Deblurring and Depth Estimation of Light Field | 300 |
DataDriven Sparse Structure Selection for Deep Neural Networks | 317 |
On the Solvability of Viewing Graphs | 335 |
Deep Volumetric Video From Very Sparse Multiview Performance Capture | 351 |
Accurate Scene Text Detection Through Border Semantics Awareness and Bootstrapping | 370 |
InteractionAware SpatioTemporal Pyramid Attention Networks for Action Classification | 388 |
Learning TypeAware Embeddings for Fashion Compatibility | 405 |
Diverse Conditional Image Generation by Stochastic Regression with Latent DropOut Codes | 422 |
ReconstructionBased Pairwise Depth Dataset for Depth Image Enhancement Using CNN | 438 |
Single Image SuperResolution with Feature Discrimination | 455 |
Domain Transfer Through Deep Activation Matching | 611 |
A Pilot Study | 627 |
Adaptively Transforming Graph Matching | 646 |
Deep Continuous Fusion for Multisensor 3D Object Detection | 663 |
Multimodal Image Alignment Through a Multiscale Chain of Neural Networks with Application to Remote Sensing | 679 |
Understanding Perceptual and Conceptual Fluency at a Large Scale | 697 |
Unsupervised Learning of MultiFrame Optical Flow with Occlusions | 713 |
DistortionAware Convolutional Filters for Dense Prediction in Panoramic Images | 732 |
Deep Randomized Ensembles for Metric Learning | 751 |
3D EgoPose Estimation via Imitation Learning | 763 |
Video and Attention | 779 |
Fully ContextAware Video Prediction | 780 |
Separating Models Maps and Metrics | 798 |
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond | 815 |
MultiAttention MultiClass Constraint for Finegrained Image Recognition | 834 |
Deep Tracking and Mapping | 851 |
869 | |
869 | |
Other editions - View all
Common terms and phrases
accuracy algorithm alignment annotations approach arXiv preprint Autoencoder baseline benchmark camera Chen classification coding Computer Vision Conference on Computer constraint convolution layers convolutional convolutional networks convolutional neural networks correspondence cross entropy dataset deep learning depth image depth map domain adaptation ECCV embedding evaluate face face recognition feature maps Fei-Fei frames global gradient graph Gray codes ground truth ICCV IEEE Conference IEEE International Conference IEEE Trans ImageNet input iterations labels LIDAR LNCS loss function matching method metric motion multi-view multiple neural networks object detection optical flow optimization outperforms output parameters Pattern Recognition CVPR performance pixels points pose estimation prediction problem proposed PSNR RANSAC reconstruction regression representation ResNet robust rPPG saliency map samples scene text sequence softmax sparse spatial Springer SSIM state-of-the-art super-resolution supervised target task tion unsupervised unsupervised learning vector Vision and Pattern visual voxel Wang Zhang