Computer Vision – ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part I

Front Matter....Pages I-XXII
Front Matter....Pages 1-1
Face Recognition from Multiple Stylistic Sketches: Scenarios, Datasets, and Evaluation....Pages 3-18
Instance-Level Coupled Subspace Learning for Fine-Grained Sketch-Based Image Retrieval....Pages 19-34
IIIT-CFW: A Benchmark Database of Cartoon Faces in the Wild....Pages 35-47
Identifying Emotions Aroused from Paintings....Pages 48-63
Fast Face Sketch Synthesis via KD-Tree Search....Pages 64-77
Front Matter....Pages 79-79
Monocular Visual-IMU Odometry: A Comparative Evaluation of the Detector-Descriptor Based Methods....Pages 81-95
Road Segmentation for Classification of Road Weather Conditions....Pages 96-108
Recognizing Text-Based Traffic Guide Panels with Cascaded Localization Network....Pages 109-121
The Automatic Blind Spot Camera: A Vision-Based Active Alarm System....Pages 122-135
Extracting Driving Behavior: Global Metric Localization from Dashcam Videos in the Wild....Pages 136-148
From On-Road to Off: Transfer Learning Within a Deep Convolutional Neural Network for Segmentation and Classification of Off-Road Scenes....Pages 149-162
Joint Optical Flow and Temporally Consistent Semantic Segmentation....Pages 163-177
Fusing Convolutional Neural Networks with a Restoration Network for Increasing Accuracy and Stability....Pages 178-191
Global Scale Integral Volumes....Pages 192-204
Aerial Scene Understanding Using Deep Wavelet Scattering Network and Conditional Random Field....Pages 205-214
Front Matter....Pages 215-215
Single-Image Insect Pose Estimation by Graph Based Geometric Models and Random Forests....Pages 217-230
Feature Augmented Deep Neural Networks for Segmentation of Cells....Pages 231-243
3-D Density Kernel Estimation for Counting in Microscopy Image Volumes Using 3-D Image Filters and Random Decision Trees....Pages 244-255
Dendritic Spine Shape Analysis: A Clustering Perspective....Pages 256-273
Cell Counting by Regression Using Convolutional Neural Network....Pages 274-290
Front Matter....Pages 215-215
Measuring Process Dynamics and Nuclear Migration for Clones of Neural Progenitor Cells....Pages 291-305
Histopathology Image Categorization with Discriminative Dimension Reduction of Fisher Vectors....Pages 306-317
Automatic Detection and Segmentation of Exosomes in Transmission Electron Microscopy....Pages 318-325
Poisson Point Processes for Solving Stochastic Inverse Problems in Fluorescence Microscopy....Pages 326-338
Deep Convolutional Neural Networks for Human Embryonic Cell Counting....Pages 339-348
Front Matter....Pages 349-349
Robust Text Detection with Vertically-Regressed Proposal Network....Pages 351-363
Scene Text Detection with Adaptive Line Clustering....Pages 364-377
From Text Detection to Text Segmentation: A Unified Evaluation Scheme....Pages 378-394
Dynamic Lexicon Generation for Natural Scene Images....Pages 395-410
End-to-End Interpretation of the French Street Name Signs Dataset....Pages 411-426
Efficient Exploration of Text Regions in Natural Scene Images Using Adaptive Image Sampling....Pages 427-439
Downtown Osaka Scene Text Dataset....Pages 440-455
Front Matter....Pages 457-457
DeepDiary: Automatically Captioning Lifelogging Image Streams....Pages 459-473
Temporal Segmentation of Egocentric Videos to Highlight Personal Locations of Interest....Pages 474-489
Face-Off: A Face Reconstruction Technique for Virtual Reality (VR) Scenarios....Pages 490-503
GPU Accelerated Left/Right Hand-Segmentation in First Person Vision....Pages 504-517
Egocentric Vision for Visual Market Basket Analysis....Pages 518-531
SEMBED: Semantic Embedding of Egocentric Action Videos....Pages 532-545
Interactive Feature Growing for Accurate Object Detection in Megapixel Images....Pages 546-556
Towards Semantic Fast-Forward and Stabilized Egocentric Videos....Pages 557-571
Front Matter....Pages 457-457
A3D: A Device for Studying Gaze in 3D....Pages 572-588
Context Change Detection for an Ultra-Low Power Low-Resolution Ego-Vision Imager....Pages 589-602
Front Matter....Pages 603-603
Label-Based Automatic Alignment of Video with Narrative Sentences....Pages 605-620
Towards Category Based Large-Scale Image Retrieval Using Transductive Support Vector Machines....Pages 621-637
Solving Multi-codebook Quantization in the GPU....Pages 638-650
Learning Joint Representations of Videos and Sentences with Web Image Search....Pages 651-667
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition....Pages 668-684
Cross-Dimensional Weighting for Aggregated Deep Convolutional Features....Pages 685-701
LOH and Behold: Web-Scale Visual Search, Recommendation and Clustering Using Locally Optimized Hashing....Pages 702-718
Front Matter....Pages 719-719
The Art of Detection....Pages 721-737
A Streamlined Photometric Stereo Framework for Cultural Heritage....Pages 738-752
Visual Link Retrieval in a Database of Paintings....Pages 753-767
Hot Tiles: A Heat Diffusion Based Descriptor for Automatic Tile Panel Assembly....Pages 768-782
Novel Methods for Analysis and Visualization of Saccade Trajectories....Pages 783-797
Adversarial Training for Sketch Retrieval....Pages 798-809
Convolutional Sketch Inversion....Pages 810-824
Detecting People in Artwork with CNNs....Pages 825-841
Transferring Neural Representations for Low-Dimensional Indexing of Maya Hieroglyphic Art....Pages 842-855
Dynamic Narratives for Heritage Tour....Pages 856-870
Convolutional Neural Networks as a Computational Model for the Underlying Processes of Aesthetics Perception....Pages 871-887
Front Matter....Pages 719-719
Pose and Pathosformel in Aby Warburg’s Bilderatlas....Pages 888-902
A New Database and Protocol for Image Reuse Detection....Pages 903-916
Back Matter....Pages 917-919