|
Papers
|
|
|
Ranking
|
|
|
Source Codes
|
|
|
Libs
|
- List of numerical libraries: several libs for performing numerical calculations (C/C++, Java, ...)
- ALGLIB: a cross-platform numerical analysis and data processing library (C/C++, C#, Pascal, VBA)
- CGAL: geometric
computation (C++)
- Eigen: C++ library for linear algebra: matrices, vectors, numerical solvers, and related algorithms
- fdlib: a frontal face detection library (C/C++, Matlab)
- GiNaC: for symbolic computation within C++
- Hybrid Toolbox for MATLAB: a MATLAB toolbox for modeling, simulating, ... (contains optimization solvers for LP/QP/MILP/MIQP)
- Libxml2: XML C parser and toolkit developed for the Gnome project (C/C++)
- Torch3vision: ML/CV (C++)
-
trimesh2
: input, output, and basic manipulation of 3D triangle meshes (C++)
|
|
Databases
|
- CV Datasets: CV
- CAVIAR: people walking, meeting, window shopping, fighting and passing out and leaving a package in a public place...
- EPFL
2: multi-camera pedestrian videos
- ETH: multi-person tracking from mobile platforms
- FDDB: dataset of face regions for studying the problem of unconstrained face detection
- iLids: UK Government benchmark datasets for automated surveillance
- PETS 2009
2: multi-view videos for tracking and surveillance
- TRECVID: multi-target tracking video dataset
- TUD 2 3: single-frame people detection and viewpoint estimation | 3D pose estimation in real-world street conditions
|
|
Tutorials
|
- Clock Work Coders (CWC): GLSL | Geometry Shader | Ray Tracing on GPU
- DirectXTutorial: DirectX
- Fallout Software: OpenGL | Windows Programming | DirectDraw | DirectInput | C/C++
- Learning From Data: introductory course on machine learning that covers the basic theory, algorithms, and applications
- Lighthouse 3D: OpenGL | VRML | Shockwave 3d (W3D)
- NEHE: OpenGL
- RasterTek: DirectX | OpenGL | Procedural Terrain | Oracle | Online Virtual World | Network Programming | Random Programming
- songho.ca: OpenGL | Digital
Signal Processing (DSP) | Math
|
|
Features
|
- Conditional Random Fields (CRF): probabilistic framework for labeling and segmenting structured data, such as sequences, trees and lattices
- Distribution Fields (DF): GIST Descriptor
: low dimensional representation of the scene | not require any form of segmentation
- Histograms of Oriented Gradient (HOG)
- HOG 2: feature descriptor | counts occurrences of gradient orientation in localized portions of an image
- HOG3D 2: 3D HOG descriptor in videos
- Local Binary Pattern (LBP) 2: texture operator
- Optical Flow (OF): pattern of apparent motion of objects, surfaces, and edges in a visual scene
|
|
Methods
|
- Boosting: general method of producing a very accurate prediction rule by combining rough and moderately inaccurate "rules of thumb"
- Branch and Bound: Branch-and-Cut & Branch-and-Price: for solving mixed integer programs (MIPs)
- Correlated Topic Model (CTM): for text or other discrete data |
models correlation between the occurrence of different topics in a document
- Dantzig-Wolfe Decomposition: for solving linear programming problems with special structure
- Golden Section Search: for finding the extremum (minimum or maximum) of a unimodal function
- Graph Cuts: for efficiently solving low-level CV problems that can be formulated in terms of energy minimization, which can be reduced to instances of the maximum flow problem in a graph
- Hungarian algorithm: solves the optimal assignment problem in polynomial time
- Kalman filter: operates recursively on streams of noisy input data to produce a statistically optimal estimate of the underlying system state
- Max-flow/min-cut
- Multi-label optimization: for many problems in CG/CV | can be efficiently solved by graph cuts
|
|
Others
|
- CV Resources: CV's papers | datasets | lectures | source codes | patents ...
- CG Resources: CG's journals | conferences | lectures | datasets | source codes ...
- CVChina: CV's news | demos | projects | source codes ...
|
