Sanja Fidler

Useful code

Conditional Random Field (CRF) inference and learning method and code by Alex Schwing, Tamir    Hazan, and Raquel Urtasun

Code for object detection with a Deformable part-based model (DPM) by Ross Girshick, Pedro    Felzenswalb, David McAllister, and Deva Ramanan

Code for bottom-up object segmentation called CPMC by Joao Carreira and Cristian Sminchisescu

Lots of useful code related to 3D scene understanding for autonomous driving by Andreas Geiger

Code for articulated pose estimation with Flexible Mixtures of Parts by Yi Yang and Deva Ramanan

Code for object detection (unfortunately no training code) with Poselets by Lubomir Bourdev,    Subhransu Maji, Thomas Brox, and Jitendra Malik

Superpixel method and code by Pablo Arbelaez, Michael Maire, Charless Fowlkes, and Jitendra Malik

SLIC superpixel code by Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal    Fua, and Sabine Süsstrunk

Xiaofeng Ren has lots of useful code including discriminative contour detection, kernel descriptors    and labeling RGB-D scenes

RGB-D Kernel Descriptors code by Liefeng Bo, Xiaofeng Ren and Dieter Fox

Scene classification method and code by Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude Oliva,    and Antonio Torralba

Andrea Vedaldi and Brian Fulkerson's VLFeat (link to paper) contains implementations of lots of    popular computer vision features and techniques

Koen Van de Sande has software for a variety of color descriptors

Nice datasets

PASCAL VOC challenge for generic object recognition, detection and segmentation by Marc    Everingham, Luc Van Gool, Chris Williams, John Winn, and Andrew Zisserman
   Keypoint and foreground mask annotations for all object classes made available by Lubomir    Bourdev, Subhransu Maji, Thomas Brox, and Jitendra Malik
   Attribute annotations for category person in PASCAL VOC 2010 made available by Lubomir Bourdev,    Subhransu Maji, and Jitendra Malik

Autonomous driving dataset called KITTI by Andreas Geiger, Philip Lenz and Raquel Urtasun

NYUv2 dataset for indoor scene segmentation from RGB-D data by Nathan Silberman, Pushmeet    Kohli, Derek Hoiem, and Rob Fergus

Sintel Flow dataset by Daniel Butler, Jonas Wulff, Garrett Stanley, and Michael Black

UIUC Pascal Sentences dataset (link to paper) by Ali Farhadi, Mohsen Hejrati, Amin Sadeghi, Peter    Young, Cyrus Rashtchian, Julia Hockenmaier, and David Forsyth

ImageNet dataset for large-scale object classification and detection by Jia Deng, Kai Li, Alex Berg,    and Fei-Fei Li

LabelMe online annotation tool and object segmentation dataset by Brian Russell, Antonio Torralba,    Kevin Murphy, and Bill Freeman

Dataset for room layout estimation by Varsha Hedau, Derek Hoiem, and David Forsyth

Monocular indoor dataset with 3D cuboid object annotation (link to paper) by Varsha Hedau, Derek    Hoiem, and David Forsyth

SUN large-scale scene recognition dataset by Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude    Oliva, and Antonio Torralba

Dataset for pose estimation and clothing parsing (link to paper) by Kota Yamaguchi, Hadi Kiapour,    Luis Ortiz, and Tamara Berg

MSRC-21 generic object class segmentation dataset (link to paper) and split by Jamie Shotton, John    Winn, Carsten Rother, and Antonio Criminisi