怖いお兄さんにプレッシャーを受けたので、差し当たり CVPR 2013 papers on the web - Papers からあとで読むリストだけ作った。全論文だと、"Dictionary Learning"がタイトルにあるのが9件もあったけどなんだろ。sparse coding系の辞書学習だと思うんだけど目新しいわけでもないしたまたま？
- Understanding Indoor Scenes using 3D Geometric Phrases
- Diffusion Processes for Retrieval Revisited
- Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
- Cartesian k-means
- Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning
- Transfer Sparse Coding for Robust Image Representation
- Boosting Binary Keypoint Descriptors
- Consensus of k-NNs for Robust Neighborhood Selection on Graph-Based Manifolds
- Deformable Graph Matching
- Graph-Based Discriminative Learning for Location Recognition
- Constraints as Features
- Cross-view Image Geolocalization
- K-means Hashing: an Affinity-Preserving Quantization Method for Learning Binary Compact Codes
- Supervised Kernel Descriptors for Visual Recognition
- Fast Convolutional Sparse Coding
- Hash Bit Selection: a Unified Solution for Selection Problems in Hashing
- Compressed Hashing
- All about VLAD
- Online Robust Dictionary Learning
- Discriminative Subspace Clustering
- A Bayesian Approach to Multimodal Visual Dictionary Learning
- Correspondence-Less Non-Rigid Registration of Triangular Surface Meshes
- Alternating Decision Forests
- Learning Class-to-Image Distance with Object Matchings
- Online Object Tracking: A Benchmark
- Robust Feature Matching with Alternate Hough and Inverted Hough Transforms
- Inductive Hashing on Manifolds
- Learning Compact Binary Codes for Visual Tracking
- Learning Binary Codes for High-dimensional Data using Bilinear Projections
- Optimized Product Quantization for Approximate Nearest Neighbor Search
- The Generalized Laplacian Distance and its Applications for Visual Matching
- Accurate Localization of 3D Objects from RGB-D Data using Segmentation Hypotheses
- Efficient Maximum Appearance Search for Large-Scale Object Detection
- Sparse Output Coding for Large-scale Visual Recognition
- Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification
- What Makes a Patch Distinct?
- Dense Non-Rigid Point-Matching Using Random Projections
- Visual Tracking via Locality Sensitive Histograms
- Improving the Visual Comprehension of Point Sets
- Fast multiple-part based object detection using KD-Ferns
- Optimizing 1-Nearest Prototype Classifiers
- Query Adaptive Similarity for Large Scale Object Retrieval
- FAsT-Match: Fast Affine Template Matching
- Lp-norm IDF for Large Scale Image Search
- Dense Segmentation-aware Descriptors
- CLAM: Coupled Localization and Mapping with Efficient Outlier Handling
- SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
- Visual Place Recognition with Repetitive Structures
- Keypoints from Symmetries by Wave Propagation
- A Fast Approximate AIB Algorithm for Distributional Word Clustering
- Learning SURF Cascade for Fast and Accurate Object Detection
- Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition
- Discriminative Color Descriptors
- Binary Code Ranking with Weighted Hamming Distance
- Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification
- Sparse Quantization for Patch Description
- Learning and calibrating per-location classifiers for visual place recognition
