Visual Recognition and Search

EECS 6890 Topics in Information Processing (3 Credits)

Spring 2013, Columbia University | Thursdays 7:00-8:50pm, 327 Seeley W. Mudd

Instructors: Rogerio Feris and Liangliang Cao {rsferis, liangliang.cao}

Home     |     Course Overview     |     Schedule     |     Resources     |     Projects     |    Presentations    |     Announcements

Important Dates

Class Topic
Student Presentations/Discussion Topics
Jan 24
CLASS 1 - Introduction [Rogerio]
SLIDES CLASS 1 [Rogerio]
 Part I: Image Representation
Jan 31
CLASS 2 - Low-level Representation: feature detection and description [Liangliang]
SLIDES CLASS 2 [Liangliang]
No student presentation in this class.
Check the ECCV 2012 Tutorial on Modern Features

Additional reading:

T. Tuytelaars and K. Mikolajczyk, Local Invariant Feature Detectors: A Survey, Foundations and Trends in Computer Graphics and Vision, 2008

J. Heinly et al, Comparative Evaluation of Binary Features, ECCV 2012
Feb 7
CLASS 3 - Mid-level Representation: feature coding and pooling [Liangliang]
SLIDES CLASS 3 [Liangliang]
Student Presentation: Sparse Coding [Kun,Yongzhou, and Yin]

J. Yang et al, Linear spatial pyramid matching using sparse coding for image classification, CVPR 2009

Y. Boureau et al, A theoretical analysis of feature pooling in visual recognition, ICML 2010

J. Wang et al, Locality-constrained Linear Coding for image classification , CVPR 2010
Feb 14
CLASS 4 - Part-based and Hierarchical Models [Rogerio]
SLIDES CLASS 4 [Rogerio]
Discussion Topic: Deformable part-based models

P. Felzenszwalb et al, Object Detection with Discriminatively Trained Part Based Models, PAMI 2010

P. Felzenszwalb et al, Cascade Object Detection with Deformable Part Models, CVPR 2010.

H. Song et al, Sparselet Models for Efficient Multiclass Object Detection, ECCV 2012
Feb 21
CLASS 5 - High-level Representation: Attributes and semantic features [Rogerio]
SLIDES CLASS 5 [Rogerio]
Discussion Topic: Relative Attributes

D. Parikh and K. Grauman, Relative Attributes, ICCV 2011

A. Kovashka et al, WhittleSearch: Image Search with Relative Attribute Feedback, CVPR 2012

A. Parkash and D. Parikh, Attributes for Classifier Feedback, ECCV 2012
 Part II : Indexing, Large-Scale Classification, and Efficient Object Detection
Feb 28
CLASS 6 - Fast Indexing and Image Retrieval [Liangliang]
SLIDES CLASS 6 [Liangliang]
Discussion Topic: Supervised hashing

B. Kulis and K. Grauman, Kernelized locality-sensitive hashing for scalable image search, ICCV 2009

L. Zhen et al, Learning to Search Efficiently in High Dimensions, NIPS 2011.

W. Liu et al, Supervised Hashing with Kernels, CVPR 2012
Mar 7
CLASS 7 - Large-Scale Image Classification [Liangliang]
SLIDES CLASS 7 [Liangliang]
Student Presentation: Web-scale visual recognition [Brendan, Jie, and Joe]

R. Raina et al, Self-taught learning: Transfer learning from unlabeled data, ICML 2007

Q. Le et al, Building high-level features using large scale unsupervised learning, ICML 2012

A. Krizhevsky et al, ImageNet Classification with Deep Convolutional Neural Networks, NIPS 2012
Mar 14
CLASS 8 - 10 Tricks for Speeding up Object Detection [Rogerio]
SLIDES CLASS 8 [Rogerio]
Discussion Topic: High-speed pedestrian detection

P. Dollar et al, The Fastest Pedestrian Detector in the West, BMVC 2010

R. Benenson et al, Pedestrian Detection at 100 frames per second, CVPR 2012

P. Dollar et al, Crosstalk Cascades for frame-rate pedestrian detection, ECCV 2012
 Spring Recess (Mar 18 – Mar 22)
 Part III : Extensions to 3D and Video
Mar 28
CLASS 9 - 3D Recognition [Rogerio]
SLIDES CLASS 9 [Rogerio]
Student Presentation: Kinect-based Human Pose Recognition [ZhongJie]

S. Izadi et al, Real-Time Human Pose Recognition in Parts from Single Depth Images, CVPR 2011
Apr 04
CLASS 10 - Video/Action recognition [Liangliang]
SLIDES CLASS 10 [Liangliang]
Student Presentation: Semantic Models for Action Recognition [Jiawei, Qian, and Chen]

S. Sadanand and J. Corso, Action Bank: A High-Level Representation of Activity in Video, CVPR 2012

L. Cao et al, Scene Aligned Pooling for Complex Video Recognition, ECCV 2012

J. Liu et al, Recognizing human actions by attributes, CVPR 2011.
 Part IV: Case Studies
Apr 11
CLASS 11 - Case Study: IBM Smart Surveillance Solution [Rogerio]
SLIDES CLASS 11 [Rogerio]
Discussion Topic: Big Datasets

A. Halevy et al, The Unreasonable Effectiveness of Data, IEEE Intelligent Systems, 2009

N. Jacobs et al, Adventures in Archiving and Using Three Years of Webcam Images, CVPR Workshop on Internet Vision, 2009

A. Torralba and A. Efros, Unbiased Look at Dataset Bias, CVPR 2011
Apr 18
CLASS 12 - Case Study: IBM Multimedia Analysis and Retrieval System [Liangliang]
demo page
Student Presentation: Geo-photo localization [Yanling, Yan, and Yaqing]

J. Hayes and A. Efros, IM2GPS: estimating geographic information from a single image, CVPR 2008

D. Crandall et al, Mapping the World's Photos, WWW 2009

C. Doersch et al, What makes Paris look like Paris, SIGGRAPH 2012
Apr 25
N/A No class. Instructors will be available by appointment. N/A N/A
May 02
N/A Student Final Project Presentation

Macro-Scale Vision: Morphology Classification in Galaxy Imagery [Brendan Jou, Joseph G. Ellis, and Jie Feng]

Large-Scale Galaxy Image Retrieval [Yin Cui, Yongzhou Xiang, and Kun Rong]

Fusing Feature Descriptors for Action Recognition in Videos [Qian Liang, Chen Xue, and Jiawei Chen]

Historical Building Finder (Columbia Tour VIDEO DEMO) [Yanling Zhang, Yaqing Mao, Yan Peng]

RGBD Face Detection [ZhongJie Bi]