March 27 (Monday) – March 29 (Wednesday)
Note: The official Program Guide is now available. It includes any updates (e.g. title changes) made to camera-ready paper. This following program uses data directly from CMT submission, but will allow participants to plan their travel schedules.
Schedule Overview
| DAY 1 - March 27 (Monday) | |||
| 8:50am | – | 9:00am | Opening Remarks |
| 9:00am | – | 10:00am | Oral Session 1 (Parallel Tracks) |
| 10:00am | – | 10:45am | Coffee Break |
| 10:45am | – | 11:45am | Oral Session 2 (Parallel Tracks) |
| 12:00pm | – | 1:00pm | Lunch |
| 1:00pm | – | 5:00pm | Tutorials |
| 5:00pm | – | 5:30pm | Break |
| 5:30pm | – | 6:30pm | Keynote Talk: Rick Szeliski, Facebook |
| 6:30pm | – | 8:00pm | Dinner |
| 7:30pm | – | 9:30pm | Posters |
| DAY 2 - March 28 (Tuesday) | |||
| 8:50am | – | 9:00am | Opening Remarks |
| 9:00am | – | 10:00am | Oral Session 3 (Parallel Tracks) |
| 10:00am | – | 10:45am | Coffee Break |
| 10:45am | – | 11:45am | Oral Session 4 (Parallel Tracks) |
| 12:00pm | – | 1:00pm | Lunch |
| 1:00pm | – | 5:00pm | Tutorials |
| 5:00pm | – | 5:30pm | Break |
| 5:30pm | – | 6:30pm | Keynote Talk: Marc Pollefeys, Microsoft/ETH Zurich |
| 6:30pm | – | 8:00pm | Dinner |
| 7:30pm | – | 9:30pm | Posters |
| DAY 3 - March 29 (Wednesday) | |||
| 8:50am | – | 9:00am | Opening Remarks |
| 9:00am | – | 10:00am | Oral Session 5 (Parallel Tracks) |
| 10:00am | – | 10:45am | Coffee Break |
| 10:45am | – | 11:45am | Oral Session 6 (Parallel Tracks) |
| 12:00pm | – | 1:00pm | Lunch |
| 1:00pm | – | 5:00pm | Tutorials |
| 5:00pm | – | 5:30pm | Break |
| 5:30pm | – | 6:30pm | Keynote Talk: Tamara Berg, Shopagon Inc/UNC-Chapel Hill |
| 6:30pm | – | 8:00pm | Dinner |
| 7:30pm | – | 9:30pm | Posters |
Oral Session papers are on the following pages
. All accepted WACV papers will give a 5 minute oral presentation with no Q/A (timing is strict). All papers will also have a poster in the evening session on the same day as their presentation. Details to the oral presentation and poster format will be sent shortly.
DAY 1 – March 27 (Monday)
Oral Session 1 (9:00am - 10:00am)
| Track 1 - Segmentation, Tracking | ||
| 1 | 136 | Deep Salient Object Detection by Integrating Multi-level Cues |
| 2 | 75 | Multi-Planar Fitting in an Indoor Manhattan World |
| 3 | 47 | Universal Skin Detection Without Color Information |
| 4 | 112 | Recurrent Fully Convolutional Networks for Video Segmentation |
| 5 | 11 | Learning Spatial Transforms for Refining Object Segment Proposals |
| 6 | 59 | Repeated Pattern Detection using CNN activations |
| 7 | 202 | Deep Context Modeling for Semantic Segmentation |
| 8 | 63 | 3D Semantic Segmentation of Modular Furniture using rjMCMC |
| 9 | 164 | PASCAL Boundaries: A Semantic Boundary Dataset with A Deep Semantic Boundary Detector |
| 10 | 210 | Can Affordances Guide Object Decomposition Into Semantically Meaningful Parts? |
| 11 | 220 | Solving occlusion problem in pedestrian detection by constructing discriminative part layers |
| 12 | 283 | Unifying Registration based Tracking: A Case Study with Structural Similarity |
| Track 2 - Action Recognition | ||
| 1 | 128 | Deep Moving Poselets for Video Based Action Recognition |
| 2 | 291 | First-person Decomposition and Zero-shot Learning |
| 3 | 119 | Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition |
| 4 | 278 | Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions |
| 5 | 169 | On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks |
| 6 | 233 | Real-time Online Action Detection Forests using Spatio-temporal Contexts |
| 7 | 152 | Ordered Pooling of Optical Flow Sequences for Action Recognition |
| 8 | 45 | Two Stream LSTM : A Deep Fusion Framework for Human Action Recognition |
| 9 | 124 | Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking |
| 10 | 199 | Efficient Action Detection in Untrimmed Videos via Multi-Task Learning |
| 11 | 130 | Learning Discriminative Features via Label Consistent Neural Network |
| 12 | 12 | Recognition of Group Activities in Videos Based on Single- and Two-Person Descriptors |
Oral Session 2 ( 10:45am – 11:45am)
| Track 1 - Computational Photo, 3D Modeling, Remote Sensing, Gesture | ||
| 1 | 23 | Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study |
| 2 | 256 | Joint Regression and Ranking for Image Enhancement |
| 3 | 113 | Material Classification under Natural Illumination using Reflectance Maps |
| 4 | 80 | Dense Batch Non-Rigid Structure from Motion in a Second |
| 5 | 32 | Global Model with Local Interpretation for Dynamic Shape Reconstruction |
| 6 | 134 | Occlusions are Fleeting - Texture is Forever: Moving Past Brightness Constancy |
| 7 | 197 | Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequences with Severe Occlusions |
| 8 | 179 | Patchwork Stereo: Scalable, Structure-aware 3D Reconstruction in Man-made Environments |
| 9 | 251 | Calibration technique for underwater active oneshot scanning system with static pattern projector and multiple cameras |
| 10 | 138 | Fast Deep Vehicle Detection in Aerial Images |
| 11 | 40 | Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery |
| 12 | 252 | Robust Hand Gestural Interaction for Smartphone based AR/VR Applications |
| 13 | 22 | Spatial-temporal motion field analysis for pixelwise crack detection on concrete surfaces |
| Track 2 - Scene Understanding, Motion Processing | ||
| 1 | 137 | 2-Line Exhaustive Searching for Real-Time Vanishing Point Estimation in Manhattan World |
| 2 | 85 | Pano2CAD: Room Layout From A Single Panorama Image |
| 3 | 102 | A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms |
| 4 | 173 | Real Estate Image Classification |
| 5 | 35 | Learn How to Choose: Independent Detectors versus Composite Visual Phrase |
| 6 | 269 | Temporal Robust Features for Violence Detection |
| 7 | 275 | SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction |
| 8 | 227 | Predicting the Perceptual Demands of Urban Driving with Video Regression |
| 9 | 29 | Optimal Threshold and LoG Based Feature Identification and Tracking of Bat Flapping Flight |
| 10 | 144 | Fast Semi Dense Epipolar Flow Estimation |
| 11 | 15 | Global Consistency Priors for Joint Part-based Object Tracking and Image Segmentation |
| 12 | 21 | Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences |
| 13 | 155 | Computing Egomotion with Local Loop Closures for Egocentric Videos |
DAY 2 – March 28 (Tuesday)
Oral Session 3 (9:00am - 10:00am)
| Track 1 - Statistical Methods, Object Recognition | ||
| 1 | 54 | Cyclical Learning Rates for Training Neural Networks |
| 2 | 72 | Guaranteed Parameter Estimation for Discrete Energy Minimization |
| 3 | 98 | Solving Robust Regularization Problems using Iteratively Re-Weighted Least Squares |
| 4 | 329 | Detecting Social Insects in Videos with Spatiotemporal Regularization |
| 5 | 171 | From Affine Rank Minimization Solution to Sparse Modeling |
| 6 | 4 | Learning Attributes from Human Gaze |
| 7 | 141 | Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes |
| 8 | 232 | Deep Learning Logo Detection with Data Expansion by Synthesising Context |
| 9 | 150 | Boosted Convolutional Neural Networks (BCNN) for Pedestrian Detection |
| 10 | 277 | Improved Deep Learning of Object Category using Pose Information |
| 11 | 295 | Learning to Recognize Objects by Retaining other Factors of Variation |
| 12 | 111 | Artistic Movement Recognition by Boosted Fusion of Color Structure and Topographic Description |
| Track 2 - Security, Vision for Aerial , Multimedia | ||
| 1 | 274 | Plug-and-Play CNN for Crowd Motion Analysis: An Application to Abnormal Event Detection |
| 2 | 200 | Deep Heterogeneous Feature Fusion for Template-Based Face Recognition |
| 3 | 225 | Integrated Global-Local Metric Learning for Person Re-identification |
| 4 | 247 | Multi-shot Person Re-identification using Part Appearance Mixture |
| 5 | 331 | Active Online Anomaly Detection using Dirichlet Process Mixture Model and Gaussian Process Classification |
| 6 | 289 | Flowdometry: An Optical Flow and Deep Learning Based Approach to Visual Odometry |
| 7 | 84 | PCA based Computation of Illumination-Invariant Space for Road Detection |
| 8 | 326 | Road Detection using Convolutional Neural Networks |
| 9 | 223 | Providing Video Annotations in Multimedia Containers for Visualization and Research |
| 10 | 307 | Detecting Sexually Provocative Images |
| 11 | 146 | Complex Event Recognition from Images with Few Training Examples |
| 12 | 239 | High Level Concepts for Affective Understanding of Images |
Oral Session 4 (10:45am – 11:45am)
| Track 1 - Vision Systems | ||
| 1 | 46 | Assessment of Peanut Pod Maturity |
| 2 | 241 | X-ray Scattering Image Classification Using Deep Learning |
| 3 | 176 | A deep learning frame-work for recognizing developmental disorders |
| 4 | 94 | When was that made? |
| 5 | 215 | Telecom Inventory management via object recognition and localisation on Google Street View Images |
| 6 | 330 | Deep Object Ranking for Template Matching |
| 7 | 302 | A Deep Learning Paradigm for Detection of Harmful Algal Blooms |
| 8 | 214 | Crime Mapping from Satellite Imagery via Deep Learning |
| 9 | 135 | Robust Road Marking Detection and Recognition Using Density-Based Grouping and Machine Learning Techniques |
| 10 | 91 | Beacon-guided Structure from Motion for Smartphone-based Navigation |
| 11 | 246 | Hardware-Centric Vision Processing for Mobile IoT Environment Exploiting Approximate Graph cut in Resistor Grid |
| 12 | 19 | Exploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance |
| Track 2 - Medical, Vision for Graphics and Robotics, Open Source API | ||
| 1 | 64 | Melanoma Detection Based on Mahalanobis Distance Learning and Constrained Graph Regularized Nonnegative Matrix Factorization |
| 2 | 10 | Size and Texture-based Classification of Lung Tumors with 3D CNNs |
| 3 | 248 | 3D-brain segmentation using deep neural network and Gaussian mixture model |
| 4 | 93 | Ultrasound tracking using ProbeSight: Camera pose estimation relative to external anatomy by inverse rendering of a prior high-resolution 3D surface map |
| 5 | 182 | Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images |
| 6 | 258 | Densification of Semi-Dense Reconstructions for Novel View Generation of Live Scenes |
| 7 | 175 | Texture attribute synthesis and transfer using feed-forward CNNs |
| 8 | 55 | A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems |
| 9 | 149 | Sparse Dictionary Learning for Identifying Grasp Locations |
| 10 | 185 | T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects |
| 11 | 319 | Gaussian Mixture Models for Temporal Depth Fusion |
| 12 | 61 | An open-source platform for underwater image and video analytics |
DAY 3 – March 29 (Wednesday)
Oral Session 5 (9:00am - 10:00am)
| Track 1 - Object Recognition 2, Large Scale Systems | ||
| 1 | 53 | Describing Unseen Classes by Exemplars: Zero-shot Learning Using Grouped Simile Ensemble |
| 2 | 324 | Deep Multi-Modal Vehicle Detection in Aerial ISR Imagery |
| 3 | 196 | Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection |
| 4 | 181 | StuffNet: Using ‘Stuff’ to Improve Object Detection |
| 5 | 125 | Towards Fine-grained Open Zero-shot Learning: Inferring Unseen Visual Features from Attributes |
| 6 | 117 | Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection |
| 7 | 74 | Fast Pedestrian Detection via Random Projection Features with Shape Prior |
| 8 | 37 | Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition |
| 9 | 195 | Box Refinement: Object Proposal Enhancement and Pruning |
| 10 | 235 | Semantic Text Summarization of Long Videos |
| 11 | 39 | Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Annotation and Scene Recognition |
| Track 2 - Industrial Inspection, VR and AR, Stereo, Evaluation | ||
| 1 | 14 | Probabilistic Surface Inference for Industrial Inspection Planning |
| 2 | 1 | Spatio-Temporal Anomaly Detection for Industrial Robots through Prediction in Unsupervised Feature Space |
| 3 | 272 | Automatic Defect Recognition in X-ray Testing using Computer Vision |
| 4 | 42 | X-ray PoseNet: 6 DoF Pose Estimation for Mobile X-ray Devices |
| 5 | 279 | Crack Segmentation by Leveraging Multiple Frames of Varying Illumination |
| 6 | 115 | GPU-accelerated real-time stixel computation |
| 7 | 67 | Model-driven Simulations for Computer Vision |
| 8 | 186 | Automatic Calibration of a Multiple-Projector Spherical Fish Tank VR Display |
| 9 | 313 | Transfer Learning and Deep Feature Extraction for Planktonic Image Data Sets |
| 10 | 234 | Fast and Robust Eyelid Outline and Aperture Detection in Real-World Scenarios |
| 11 | 298 | On Crater Verification Using Mislocalized Crater Regions |
Oral Session 6 (10:45am – 11:45am)
| Track 1 - Face Processing, Biometrics, Image Compression, HCI | ||
| 1 | 27 | Robust 3D Patch-Based Face Hallucination |
| 2 | 49 | Dictionary Alignment for Low-Resolution and Heterogeneous Face Recognition |
| 3 | 293 | Pose-Robust Face Verification by Exploiting Competing Tasks |
| 4 | 79 | Deep Feature Consistent Variational Autoencoder |
| 5 | 183 | Egocentric Height Estimation |
| 6 | 92 | Gender-From-Iris or Gender-From-Mascara? |
| 7 | 259 | ContlensNet: Robust Iris Contact Lens Detection Using Deep Convolutional Neural Networks |
| 8 | 310 | Breathing Rate Monitoring during Sleep from a Depth Camera under Real-life Conditions |
| 9 | 120 | Writer Identification in Noisy Handwritten Documents |
| 10 | 294 | Image Set Classification Using Sparse Bayesian Regression |
| 11 | 267 | Bandwidth limited object recognition in high resolution imagery |
| 12 | 62 | Personalized Image Aesthetic Quality Assessment by Joint Regression and Ranking |
| Track 2 - Human Motion, Image Indexing, Vision Systems | ||
| 1 | 292 | Deep spatio-temporal features for multimodal emotion recognition |
| 2 | 56 | Human Pose Estimation using Deep Structure Guided Learning |
| 3 | 73 | Switching Linear Inverse-Regression Model for Tracking Head Pose |
| 4 | 83 | Deep Image Set Hashing |
| 5 | 280 | Learning Effective Binary Descriptors via Cross Entropy |
| 6 | 160 | Convolutional Sparse and Low-Rank Coding-Based Rain Streak Removal |
| 7 | 162 | Fast, accurate, small-scale 3D scene capture using a low-cost depth sensor |
| 8 | 153 | Who Moved My Cheese? Automatic Annotation of Rodent Behaviors with Convolutional Neural Networks |
| 9 | 90 | Temporally Coded Illumination for Rolling Shutter Motion De-blurring |
| 10 | 139 | Text-Edge-Box: An Object Proposal Approach for Scene Texts Localization |
| 11 | 224 | Distance Penalization and Fusion for Person Re-identification |