Source code for spatio-temporal descriptor, interest point detector, face recognition, etc (LEAR Lab)
Computer Vision Central - Posted on December 11, 2011 at 3:33 pm.
Spatio-Temporal Descriptor for Action Recognition (HOG3D)
The software for computing the spatio-temporal descriptor using gradient orientations and regular polyhedrons (or platonic solids) - as described in our BMVC'08 paper - can be found on the website of Alexander Kläser.
Dense Trajectories Video Description
Metric Learning for verification and Multiple Instance LearningMatthieu Guillaumin's LDML and MildML on his code page.
Interest Point Detectors & Test Sequences
A joint comparison of affine covariant regions by LEAR, Oxford, Leuven and Prague (the test setup and the binaries are available)
Binaries and test images for Krystian Mikolajczyk's scaled and affine interest point detectors and various types of local image descriptors.
Gyuri Dorko's version of these detectors.
Object Detection and Localization Toolkit
You may download the Navneet Dalal's object detection and localization toolkit from here.
Groups of adjacent contour segments
Software for detecting Vitto's local shape features (see bottom of page).
Texture Based Image Classification
YORG, developed within the AceMedia project helps organizing photo collections.
Trecvid example generator
This program generates example videos for the Trecvid copy detection task.