Datasets
- Annotations PASCAL VOC 2007, 2010 animal datasets available: Strong supervision for part based models project page
- KTH Multiview Football Dataset II
Multiview images of professional football players with ground truth 3D pose. Details of the dataset:
- KTH Multiview Football Dataset I [zip file]
This dataset consists of images from 3 different cameras of 3 professional footballers during a match of the Allsvenskan league.
- 771 images of football players
- Includes images taken from 3 views at 257 time instances
- 14 annotated body joints
- W31 Dataset images [zip file] and W31 Dataset annotations [.mat file]
This data set consists of 31 videos capturing the visual experience of a subject walking from a metro station to work, subsampled at 1 HZ.
- 7236 images in total
- Each image is annotated with a location id which covers 9 unique labels in total.
- Temporal segments corresponding to novel ego motions are annotated as well.
- W12 Dataset images and annotations [zip file]
This dataset consists of multiple images of 12 different places a subject goes through when walking from a metro station to work.
- 142 images
- Each image is annotated with a location id
- Objects/people which do not belong to the static environment are labeled in each image (segmentation ground truth).
Software
-
Detection and visualization code
This file contains the code used in the publication:
Object Detection Using Strongly-Supervised Deformable Part Models, H. Azizpour and I. Laptev, ECCV 2012.
Visit the paper's project website for more details: Strong supervision for part based models - Distance Transforms 1-4 Dimensional [Matlab Code]
Written and maintained by Vahid Kazemi.
-
Iterative methods for computation of Fundamental matrix [Matlab Code]
The package contains MATLAB implementations of the iterative algorithms suggested in Hartley and Zisserman's MultiView Geometry.
Written and maintained by Omid Aghazadeh.
-
Nonlinear Coupled Diffusion [Matlab Code]
The package contains MATLAB implementation of Weickert's Nonlinear Coupled Diffusion.
Written and maintained by Omid Aghazadeh.
-
A Sparse Set of Features for Texture Discrimination [Matlab Code]
The package contains a MATLAB implementation of Brox's feature set.
Written and maintained by Omid Aghazadeh.
-
Gaussian Mixture Models on Cuda Mex [Binaries] [Requires Fermi Cards]
The package contains linux 64 bit binaries for learning (Expectation Maximization) and evaluating multi dimensional Gaussian mixture models using GPU acceleration.
Written and maintained by Omid Aghazadeh.
-
Isotropic Multi Dimensional Kernel Density Estimation on Cuda Mex [Binaries] [Requires Fermi Cards]
The Linux 64 bit binary for MDKDE(Isotropic) using GPU acceleration.
Written and maintained by Omid Aghazadeh.
-
Dense distance computations between two sets of points [Binaries] [Requires Fermi Cards]
The Linux 64 bit binary for dense distance computations including P norms(L_1, L_2 and L_inf), Chi squared distance and Histogram Intersection between two sets of points(or histograms) using GPU acceleration. The code is tuned to handle large dimensions and large sets (when the distance matrix does not fit on device memory).
Written and maintained by Omid Aghazadeh.