3D face (facial expressions) databases
- Bosphorus database (face & hand)
- Morphace
- Analyzing facial expressions in three dimensional space
- Face recognition
- CASIA 3D face database
- BJUT-3D face database
Human detection
- Dataset and ground-truth
- Papers:
- Piotr Dollár’s work
- 09 BMVC - Integral Channel Features
- 10 BMVC - The Fastest Pedestrian Detector in the West
- 12 ECCV - Crosstalk Cascades for Frame-Rate Pedestrian Detection
- 12 PAMI - Pedestrian Detection: An Evaluation of the State of the Art
- 14 PAMI - Fast Feature Pyramids for Object Detection
- Piotr Dollár’s work
- Other:
Human Pose Estimation
- Dataset and Benchmark
- Papers
Object tracking
- Dataset and ground-truth
Single camera tracking:
Online object tracking:
- Visual Tracker Benchmark
- Visual Object Tracking (VOT) challenge
- 13 CVPR - Online Object Tracking: A Benchmark
13 ICCV - Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines
Deep Learning based trackers:
- 15 ICML - Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
- 15 arXiv - Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
Tracking-by-detection/data-association:
- 14 PAMI - Continuous Energy Minimization for Multi-Target Tracking: with MATLAB code
- 14 CVPR - Occlusion Geodesics for Online Multi-Object Tracking: with MATLAB code
- 12 CVPR - Discrete-Continuous Energy Minimization for Multi-Target Tracking: with MATLAB code
- 12 CVPR - Multi-Target Tracking by Online Learning of Non-linear Motion Patterns and Robust Appearance Models
- 12 AVSS - Online Multi-Person Tracking by Tracker Hierarchy: with C++ code
- 11 CVPR - Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects: with MATLAB code
- Multiple camera tracking:
Saliency detection
Image feature detection and description 1
Keypoint detectors
- FAST: high-speed corner detector, in OpenCV
- AGAST: even faster than the FAST. A multi-scale version of this method is used for the BRISK descriptor (10 ECCV).
Binary descriptors
- BRIEF – fast and accurate interest point descriptor (not invariant to rotations and scale)
- ORB – Oriented-Brief descriptor (invariant to rotations, but not scale), in OpenCV
- BRISK – efficient binary descriptor invariant to rotations and scale, in OpenCV
- FREAK – faster than BRISK (invariant to rotations and scale), in OpenCV
SIFT & SURF Implementations
- SIFT: Original code by David Lowe | OpenCV | OpenSIFT | GPU
- SURF: Herbert Bay’s code | OpenCV | CUDA
Other Local Feature Detectors and Descriptors
- VGG Affine Covariant features – Oxford code for various affine covariant feature detectors and descriptors
- LIOP descriptor – Local Intensity Order Pattern (LIOP) descriptor
- Local Symmetry Features – matching of local symmetry features under large variations in lighting, age, and genTocHereg style
Global Image Descriptors
- GIST: MATLAB | C++ (Lear’s version)
- CENTRIST (in
libHIK
) – global visual descriptor for scene categorization and object detection. Another version can be found here.
Image deblur
- Overview by cwang: Deblur-related Materials
Image Dehaze
Steoro matching
- 14 PAMI - Stereo Matching Using Tree Filtering
- 04 CVPR - Efficient Belief Propagation for Early Vision
Filtering
- Bilateral Filtering: 14 PAMI - Hardware-Efficient Bilateral Filtering for Stereo Matching (integrated)
1. Source page of SYSU: http://gitl.sysu.edu.cn/downloads. ↩