Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I

Front Matter....Pages -
Visual Tracking by Sampling Tree-Structured Graphical Models....Pages 1-16
Tracking Interacting Objects Optimally Using Integer Programming....Pages 17-32
Learning Latent Constituents for Recognition of Group Activities in Video....Pages 33-47
Large-Scale Object Classification Using Label Relation Graphs....Pages 48-64
30Hz Object Detection with DPM V5....Pages 65-79
Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection....Pages 80-94
Linking People in Videos with “Their” Names Using Coreference Resolution....Pages 95-110
Optimal Essential Matrix Estimation via Inlier-Set Maximization....Pages 111-126
UPnP: An Optimal O ( n ) Solution to the Absolute Pose Problem with Universal Applicability....Pages 127-142
3D Reconstruction of Dynamic Textures in Crowd Sourced Data....Pages 143-158
3D Interest Point Detection via Discriminative Learning....Pages 159-173
Pose Locality Constrained Representation for 3D Human Pose Reconstruction....Pages 174-188
Synchronization of Two Independently Moving Cameras without Feature Correspondences....Pages 189-204
Multi Focus Structured Light for Recovering Scene Shape and Global Illumination....Pages 205-219
Coplanar Common Points in Non-centric Cameras....Pages 220-233
SRA: Fast Removal of General Multipath for ToF Sensors....Pages 234-249
Sub-pixel Layout for Super-Resolution with Images in the Octic Group....Pages 250-264
Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition....Pages 265-280
Read My Lips: Continuous Signer Independent Weakly Supervised Viseme Recognition....Pages 281-296
Multilinear Wavelets: A Statistical Shape Space for Human Faces....Pages 297-312
Distance Estimation of an Unknown Person from a Portrait....Pages 313-327
Probabilistic Temporal Head Pose Estimation Using a Hierarchical Graphical Model....Pages 328-344
Description-Discrimination Collaborative Tracking....Pages 345-360
Online, Real-Time Tracking Using a Category-to-Individual Detector....Pages 361-376
Robust Visual Tracking with Double Bounding Box Model....Pages 377-392
Tractable and Reliable Registration of 2D Point Sets....Pages 393-406
Graduated Consistency-Regularized Optimization for Multi-graph Matching....Pages 407-422
Optical Flow Estimation with Channel Constancy....Pages 423-438
Non-local Total Generalized Variation for Optical Flow Estimation....Pages 439-454
Learning Brightness Transfer Functions for the Joint Recovery of Illumination Changes and Optical Flow....Pages 455-471
Hipster Wars: Discovering Elements of Fashion Styles....Pages 472-488
From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields....Pages 489-504
Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis....Pages 505-519
Learning to Rank 3D Features....Pages 520-535
Salient Color Names for Person Re-identification....Pages 536-551
Learning Discriminative and Shareable Features for Scene Classification....Pages 552-568
Image Retrieval and Ranking via Consistently Reconstructing Multi-attribute Queries....Pages 569-583
Neural Codes for Image Retrieval....Pages 584-599
Architectural Style Classification Using Multinomial Latent Logistic Regression....Pages 600-615
Instance Segmentation of Indoor Scenes Using a Coverage Loss....Pages 616-631
Superpixel Graph Label Transfer with Learned Distance Metric....Pages 632-647
Precision-Recall-Classification Evaluation Framework: Application to Depth Estimation on Single Images....Pages 648-662
A Multi-stage Approach to Curve Extraction....Pages 663-678
Geometry Driven Semantic Labeling of Indoor Scenes....Pages 679-694
A Novel Topic-Level Random Walk Framework for Scene Image Co-segmentation....Pages 695-709
Surface Matching and Registration by Landmark Curve-Driven Canonical Quasiconformal Mapping....Pages 710-724
Motion Words for Videos....Pages 725-740
Activity Group Localization by Modeling the Relations among Participants....Pages 741-755
Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach....Pages 756-771
Semantic Aware Video Transcription Using Random Forest Classifiers....Pages 772-786
Ranking Domain-Specific Highlights by Analyzing Edited Videos....Pages 787-802
A Multi-transformational Model for Background Subtraction with Moving Cameras....Pages 803-817
Visualizing and Understanding Convolutional Networks....Pages 818-833
Part-Based R-CNNs for Fine-Grained Category Detection....Pages 834-849
Back Matter....Pages -