IEEE CVPR 2012
TechTalks from event: IEEE CVPR 2012
- All Talks
- From Pixels to Physics: Probabilistic Color De-rendering
- Decomposing Global Light Transport using Time of Flight Imaging
- Accidental Pinhole and Pinspeck Cameras: Revealing the Scene Outside the Picture
- Jigsaw Puzzles with Pieces of Unknown Orientation
- Affine-Invariant, Elastic Shape Analysis of Planar Contours
- Progressive Graph Matching: Making a Move of Graphs via Probabilistic Voting
- The Shape Boltzmann Machine: A Strong Model of Object Shape
- Surface Regions of Interest for Viewpoint Selection
- Camera Spectral Sensitivity Estimation from a Single Image under Unknown Illumination by using Fluorescence
- Micro Phase Shifting
- A Closed-Form Solution to Uncalibrated Photometric Stereo via Diffuse Maxima
- Connected Contours: A New Contour Completion Model that Respects the Closure Effect
- Respects the Closure Effect On Multiple Foreground Cosegmentation
- Weakly Supervised Structured Output Learning for Semantic Segmentation
- A Unified Approach to Salient Object Detection via Low Rank Matrix Recovery
- Invited Talk 1
- Invited Talk 2
- Award
- Video from Nearly Still: An Application to Low Frame-rate Gait Recognition
- What Are We Looking For: Towards Statistical Modeling of Saccadic Eye Movements and Visual Saliency
- Stream-based Joint Exploration-Exploitation Active Learning
- Incremental Gradient on the Grassmannian for Online Foreground and Background Separation in Subsampled Video
- Curvature-Based Regularization for Surface Approximation
- A-Optimal Non-negative Projection for Image Representation
- A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization
- On Template-Based Reconstruction from a Single View: Analytical Solutions and Proofs of Well-Posedness for Developable, Isometric and Conformal Surfaces
- An Online Learned CRF Model for Multi-Target Tracking
- Robust Visual Tracking via Multi-Task Sparse Learning
- Learning Rotation-Aware Features: From Invariant Priors to Equivariant Descriptors
- QsRank: Query-sensitive Hash Code Ranking for Efficient ?-neighbor Search
- Geodesic Flow Kernel for Unsupervised Domain Adaptation
- Supervised Hashing with Kernels
- All you want to know about Gaussian Processes - Part 1
- All you want to know about Gaussian Processes - Part 2
- Large-Scale Visual Recognition
- Domain Transfer Learning for Vision Applications
- Compressive Sensing for Videos
- Deep Learning Methods for Vision - Part 1
- Deep Learning Methods for Vision - Part 1
- Applied Bayesian Nonparametrics
- Vision Applications on Mobile Using OpenCV
- Computer Vision on Rolling Shutter Cameras
- Advanced 3D Image Processing with Point Cloud Library (PCL)
- Discriminative Illumination: Per-Pixel Classification of RawMaterials based on Optimal Projections of Spectral BRDF
- Discriminative Illumination: Per-Pixel Classification of RawMaterials based on Optimal Projections of Spectral BRDF
- Detecting Activities of Daily Living in First-person Camera Views
- Discriminative Virtual Views for Cross-View Action Recognition
- Max-Margin Early Event Detectors
- Understanding Collective Crowd Behaviors: Learning a Mixture Model of Dynamic Pedestrian-Agents
- Face Detection, Pose Estimation, and Landmark Localization in the Wild
- Face Alignment by Explicit Shape Regression
- Contextual Boost for Pedestrian Detection
- Pedestrian Detection at 100 Frames per Second
- Street-to-Shop: Cross-Scenario Clothing Retrieval via Parts Alignment and Auxiliary Set
- Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach
- A Theory of Multi-Layer Flat Refractive Geometry
- Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite
- Teaching 3D Geometry to Deformable Part Models
- Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features
- Semantic Segmentation using Regions and Parts
- Large-scale Image Classification with Trace-norm Regularization
- Structured Prediction and Learning in Computer Vision
- Self Driving Cars
- Opening Remarks