Reproducible Research in Computer Vision
Image segmentation, parsing and matting
- Image segmentation by normalized cut Ncut
- Epitome-based image segmentation epitome
- Bayesian multiscale image segmentation SMAP
- Graph-cut based image segmentation segment GC code2
- EDISON system EDISON EDISON code2
- Pfinder system Pfinder
- A closed form solution to image matting matting
- Spectral matting SpecMatt code
- Level set evolution without reinitialization LSE code
- Implicit active contour driven by local binary fitting energy IAC-LBF code
- Snakes, shapes, and gradient vector flow GVF-snake code
- Unsupervised learning of finite mixture model FMM code
- DDMCMC image segmentation
- Image segmentation by generalized SW-cuts
- A generalized model for scratch detection
- Biased normalized cut
- Power watersheds (iccv'2009) PW code
- Global contrast based salient region detection
- Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities SW code
- Interactive segmentation toolbox (GrabCut+LazySnap)
- Geodesic star convexity for interactive image segmentation
- Distributed cosegmentation via submodular optimization on anisotropic diffusion SOAD code
- Segmenting scenes by matching image composites
- Automatic image segmentation by dynamic region merging DRM code
- Interactive images: Cuboid proxies for smart image manipulation
- Efficient inference in fully connected CRFs with Gaussian edge potentials
- Image segmentation with cascaded hierarchical models and logistic disjunctive normal networks CHM-LDNN ode
- Nonlocal matting
- KNN matting
- Unsupervised joint object discovery and segmentation in Internet Images
Object detection/recognition
- Adaboost method Adaboost code
- Biologically inspired object recognition BioInspired code
- Hierarchical models of object recognition in cortex HMO code
- Scalable recognition with a vocabulary tree vocab_tree code
- Shock graphs ShockGraph code
- Shape contexts ShapeContext code
- Robust nonrigid point matching RNPM code
- Histograms of Oriented Gradients HOG code
- Pyramid histogram of oriented gradient
- Beyond bag of features BBoF code
- SuperParsing SuperParsing code
- Aggregating gradient distributions into intensity orders
- Matching local self-similarities across images and videos Local Self-Similarities Code (third-party implementation)
- Deformed lattice detection in real-world images
- Feature-centric efficient subwindow search FCE code
- Poselets: Body part detectors trained using 3D human pose annotations Poselets code
- Ensemble of Exemplar-SVMs for object detection and beyond
- Discriminative learning of relaxed hierarchy for large-scale visual recognition LSVR code
- Multiple kernels for object detection
- Toward total scene understanding: Classification, annotation and segmentation in an automatic framework
- Object bank: A high-level image representation for scene classification and semantic feature sparsification
- Informative feature selection for object recognition via Sparse PCA SparsePCA code
- Linear spatial pyramid matching using sparse coding for image classification LSPM code
- Locality-constrained linear coding for image classification LLC code
- MIT LabelMe open annotation tool
- Stream-based joint exploration-exploitation active learning EEAL code
- BoF meets HOG: Feature extraction based on histograms of oriented p.d.f cradients for image classification BoF-HOG code
- Discriminatively trained deformable part models
- Joint deep learning for pedestrian detection
Visual tracking
- Incremental learning for robust visual tracking IVT code
- Online visual tracking with histograms and articulating blocks HAB code
-
Speeded-Up Robust Features
- Histogram of oriented gradients-based human detection
- HOGgles: Visualizing object detection features
- Visual tracking using appearance model and particle filters
- Video object segmentation by tracking regions TrackRegion code
- Visual tracking decomposition
- Robust visual tracking using L1 minimization L1track code
- Visual tracking via adaptive structural local sparse appearance model
- Robust object tracking via sparsity-based collaborative model
- Discrete-continuous optimization for multi-target tracking
- Multi-target tracking by continuous energy minimization
- Distribution fields for tracking
- Least soft-threshold squares Tracking LSTST code
- HOGgles: Visualizing object detection features
- Online robust non-negative dictionary learning for visual tracking
- The way they move: tracking targets with similar appearance
- Real-time compressive tracking
Action/event/scene recognition
- Human activity detection from RGBD Images
- Action MACH: a spatio-temporal maximum average correlation height filter for action recognition
- Evaluation of local spatio-temporal features for action recognition
- 2D action recognition serves 3D human pose estimation
- Hierarchical mean shift, space-time segmentation and action recognition
- Human activity recognition with metric learning
- A Hough transform-based voting framework for action recognition Code
- Learning hierarchical spatio-temporal features for action recognition with independent subspace analysis
- Recognizing scene viewpoint using panoramic place representation
- Multimodal decomposable models for human pose estimation