PmWiki.Software History
Hide minor edits - Show changes to output
Added lines 1-6:
! Tiny Images Dataset download
The entire 80 million Tiny Image dataset can be downloaded [[http://horatio.cs.nyu.edu/mit/tiny/data/index.html|here]].
----
The entire 80 million Tiny Image dataset can be downloaded [[http://horatio.cs.nyu.edu/mit/tiny/data/index.html|here]].
----
Changed lines 22-23 from:
to:
[[http://cs.nyu.edu/~fergus/research/fergus_iccv05_google_validation.tgz|Google validation set from ICCV'05 paper]]
Changed lines 36-38 from:
Oxford Robotics Reading Group on EM
to:
----
!Oxford Robotics Reading Group on EM
!Oxford Robotics Reading Group on EM
Added line 22:
Added line 25:
Changed line 40 from:
to:
[[http://cs.nyu.edu/~fergus/research/tutorial_em.ppt|Powerpoint slides]]. Demo [[http://cs.nyu.edu/~fergus/research/tutorial_em_matlabcode.zip|Matlab code]] for 2-D Gaussian mixtures
Changed lines 22-30 from:
Train
Caltech test data
Constellation Model
I have code available for distribution for both the CVPR'03 paper "Object Class Recognition by Unsupervised Scale
to:
[[Ghttp://cs.nyu.edu/~fergus/research/fergus_iccv05_google_validation.tgz|oogle validation set from ICCV'05 paper]]
[[http://cs.nyu.edu/~fergus/research/iccv05_frame_ind.tgz|Train/test frame indices from ICCV'05 paper]]
[[http://cs.nyu.edu/~fergus/research/fergus_iccv05_watchleopardguitar.zip|Caltech test data: Guitars, Leopards, Wrist Watches used for testing in ICCV'05 Google paper]]
----
!Constellation Model. Code for CVPR'03 and CVPR'05 papers.
I have code available for distribution for both the CVPR'03 paper "Object Class Recognition by Unsupervised Scale-Invariant Learning" and also the CVPR'05 paper "A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition". The CVPR'03 code is Linux only. The CVPR'05 code works under both Windows and Linux and uses the [[http://vxl.sourceforge.net/|VXL]] libraries. Please email me if you would like the code.
[[http://cs.nyu.edu/~fergus/research/iccv05_frame_ind.tgz|Train/test frame indices from ICCV'05 paper]]
[[http://cs.nyu.edu/~fergus/research/fergus_iccv05_watchleopardguitar.zip|Caltech test data: Guitars, Leopards, Wrist Watches used for testing in ICCV'05 Google paper]]
----
!Constellation Model. Code for CVPR'03 and CVPR'05 papers.
I have code available for distribution for both the CVPR'03 paper "Object Class Recognition by Unsupervised Scale-Invariant Learning" and also the CVPR'05 paper "A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition". The CVPR'03 code is Linux only. The CVPR'05 code works under both Windows and Linux and uses the [[http://vxl.sourceforge.net/|VXL]] libraries. Please email me if you would like the code.
Changed line 18 from:
Google images and labels from ICCV'05 paper
to:
[[http://cs.nyu.edu/~fergus/research/fergus_iccv05_google.tgz|Google images and labels from ICCV'05 paper]]
Changed lines 3-4 from:
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
to:
The code package includes the Matlab source code used in the paper, a comprehensive [[http://cs.nyu.edu/~fergus/research/deblur/README|README]] file and sample images. Please fill in the form [[http://cs.nyu.edu/~fergus/deblur_code_form.html|here]] and I will email you the code.
----
----
Changed line 11 from:
to:
Added lines 1-4:
!Removing Camera Shake from a Single Image. Code for SIGGRAPH 2006 paper.
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
Changed lines 7-8 from:
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the [[http://cs.nyu.edu/~fergus/code/ipp_timings.txt|timings]]. MEX file source mexopts.sh MEX configuration Matlab test script
to:
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the [[http://cs.nyu.edu/~fergus/code/ipp_timings.txt|timings]]. [[http://cs.nyu.edu/~fergus/code/ipp_mt_conv2.cpp|MEX file source]], [[http://cs.nyu.edu/~fergus/code/mexopts.sh|mexopts.sh MEX configuration]], [[http://cs.nyu.edu/~fergus/code/conv_test.m|Matlab test script]].
Deleted lines 9-12:
Removing Camera Shake from a Single Image. Code for SIGGRAPH 2006 paper.
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
Changed line 3 from:
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the timings. MEX file source mexopts.sh MEX configuration Matlab test script
to:
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the [[http://cs.nyu.edu/~fergus/code/ipp_timings.txt|timings]]. MEX file source mexopts.sh MEX configuration Matlab test script
Changed lines 11-17 from:
This course reviews current methods for object category recognition, dividing them into four main areas: bag-of-words models; parts and structure models; discriminative methods and combined recognition and segmentation. The emphasis will be on the important general concepts rather than in depth coverage of contemporary papers. The course is accompanied by extensive Matlab demos.
Learning Object Categories from Google's Image Search. Datasets from ICCV 2005 paper.
to:
----
!Learning Object Categories from Google's Image Search. Datasets from ICCV 2005 paper.
!Learning Object Categories from Google's Image Search. Datasets from ICCV 2005 paper.
Added lines 1-39:
!Fast 2D image convolution MEX file for Matlab under Linux.
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the timings. MEX file source mexopts.sh MEX configuration Matlab test script
----
Removing Camera Shake from a Single Image. Code for SIGGRAPH 2006 paper.
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
Recognizing and Learning Object Categories. ICCV 2005 Short Course. Link
This course reviews current methods for object category recognition, dividing them into four main areas: bag-of-words models; parts and structure models; discriminative methods and combined recognition and segmentation. The emphasis will be on the important general concepts rather than in depth coverage of contemporary papers. The course is accompanied by extensive Matlab demos.
Learning Object Categories from Google's Image Search. Datasets from ICCV 2005 paper.
The .tgz file below contains the images of the seven categories collected from Google which were used in our ICCV'05 paper, "Learning Object Categories from Google's Image Search".
Google images and labels from ICCV'05 paper
The 7 classes are: Airplane, Cars Rear, Face, Guitar, Leopard, Motorbike, Wrist Watch. In each subdirectory, the labels are contained within a Matlab file, Ground_Truth.mat. This has a tri-state label for each image. 0 = Junk, 1 = Intermediate and 2 = Good Example. The labeling was performed by an individual who has no knowledge of the algorithm.
Google validation set from ICCV'05 paper
Train/test frame indices from ICCV'05 paper
Caltech test data: Guitars, Leopards, Wrist Watches used for testing in ICCV'05 Google paper
Constellation Model. Code for CVPR'03 and CVPR'05 papers.
I have code available for distribution for both the CVPR'03 paper "Object Class Recognition by Unsupervised Scale-Invariant Learning" and also the CVPR'05 paper "A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition". The CVPR'03 code is Linux only. The CVPR'05 code works under both Windows and Linux and uses the VXL libraries. Please email me if you would like the code.
Oxford Robotics Reading Group on EM
Here are some materials from the reading group I gave on EM in Oxford on 24/05/05.
Powerpoint slides. Demo Matlab code for 2-D Gaussian mixtures
Wrapper for Intel's Integrated Performance Primitives (IPP) libraries, also using OpenMP multi-threading. Requires 64-bit Intel CPU, up to date IPP libraries and Intel Compiler. Runs 5x-25x faster than Matlab's conv2 (or fft2 if kernel is large), check out the timings. MEX file source mexopts.sh MEX configuration Matlab test script
----
Removing Camera Shake from a Single Image. Code for SIGGRAPH 2006 paper.
The code package includes the Matlab source code used in the paper, a comprehensive README file and sample images. Please fill in the form here and I will email you the code.
Recognizing and Learning Object Categories. ICCV 2005 Short Course. Link
This course reviews current methods for object category recognition, dividing them into four main areas: bag-of-words models; parts and structure models; discriminative methods and combined recognition and segmentation. The emphasis will be on the important general concepts rather than in depth coverage of contemporary papers. The course is accompanied by extensive Matlab demos.
Learning Object Categories from Google's Image Search. Datasets from ICCV 2005 paper.
The .tgz file below contains the images of the seven categories collected from Google which were used in our ICCV'05 paper, "Learning Object Categories from Google's Image Search".
Google images and labels from ICCV'05 paper
The 7 classes are: Airplane, Cars Rear, Face, Guitar, Leopard, Motorbike, Wrist Watch. In each subdirectory, the labels are contained within a Matlab file, Ground_Truth.mat. This has a tri-state label for each image. 0 = Junk, 1 = Intermediate and 2 = Good Example. The labeling was performed by an individual who has no knowledge of the algorithm.
Google validation set from ICCV'05 paper
Train/test frame indices from ICCV'05 paper
Caltech test data: Guitars, Leopards, Wrist Watches used for testing in ICCV'05 Google paper
Constellation Model. Code for CVPR'03 and CVPR'05 papers.
I have code available for distribution for both the CVPR'03 paper "Object Class Recognition by Unsupervised Scale-Invariant Learning" and also the CVPR'05 paper "A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition". The CVPR'03 code is Linux only. The CVPR'05 code works under both Windows and Linux and uses the VXL libraries. Please email me if you would like the code.
Oxford Robotics Reading Group on EM
Here are some materials from the reading group I gave on EM in Oxford on 24/05/05.
Powerpoint slides. Demo Matlab code for 2-D Gaussian mixtures