CS 884
Advanced Topics in Computer Vision and Robotics

Time/Location: Tuesday 4:30-7:10,   Innovation Hall 208
Instructor: Dr. Jana Kosecka
Office: 4444, Research II
email: kosecka@cs.gmu.edu
Course website http://cs.gmu.edu/~kosecka/cs884/

Announcements

Get familiar with Matlab and OpenCV

Schedule (subject to change)


Date   Topic/Readings Presenter Assignments/Resources
Aug 27   Introduction and course logistics (slides)
  Local and Global features (slides)
JK
Sept 3   Local and Global features Cont. (slides)
  Machine Learning Methods (part 1 slides)
  1. Scalable Recognition with a Vocabulary Tree; D. Nister and H. Stewenius, CVPR 2006
JK
Sept 10   Object Instance Recognition/Retrieval
  Machine Learning Methods (part 2 slides)
  1. Video Google; J. Sivic and A. Zisserman, ICCV 2003
  2. Object Retrieval with Large Vocabularies and Fast Spatial Matching Philbin, J. and Chum, O. and Isard, M. and Sivic, J. and Zisserman, CVPR 2007
  3. Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases Philbin, J. and Chum, O. and Isard, M. and Sivic, J. and Zisserman, A. In CVPR 2008
  4. Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval; Chum, O. and Philbin, J. and Sivic, J. and Isard, M. and Zisserman, A., ICCV 2007
  5. Mark Cummins and Paul Newman FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance. IJRR, 27(6):647-665. 2008
  6. View-based maps; K. Konolige, J. Bowman, J. D. Chen, P. Mihelich, M. Calonder, V. Lepetit and P. Fua, RSS 2009
  • Local Invariant Feature Detectors: A Survey; T. Tuytelaars, K. Mikolajcsyk, 2008
  • SIFT features paper (.pdf)
Sept 17   Object Detection, Categorization, Global Models
  Machine Learning Methods (part 3)
  1. Hamming Embedding and Weak Geometry Consistency for Large Scale Image Search; Herve Jegou; Matthijs Douze; Cordelia Schmid (GL)
  2. Beyond Bags of Features; Spatial Pyramid Matching for Recognizing Natural Scene Categories; Lazebnik, Schmid and Ponce, CVPR 2006 (MR)
  3. K. Grauman; Pyramid match hashing: Sub-linear time indexing over partial correspondences (2007)
  4. Histogram of oriented Gradients for Human detection; N. Dalal and B. Triggs, CVPR 2005 (JK)
  5. Rapid Object Detection Using Boosted Cascade of Simple Features; Viola and Jones, CVPR 2001 (JK)
Sept 24   Part based models, Boosting slides
  1. Christoph Lampert, Matthew Blaschko, and Thomas Hofmann. Beyond Sliding Windows: Object Localization by Efficient Subwindow Search. CVPR 2008
  2. D. Ramanan, X. Ren; Histograms of Sparse Codes for Object Detection
  3. T. Dean et.al; Fast, Accurate Detection of 100,000 Object Classes on a Single Machine, CVPR 2013
  4. A Discriminatively Trained Multiscale Deformanble Part Based Models; Felzenswalb et. al CVPR 2008 (JK)
  5. Combined Object Categorization and Segmentation with an Implicit Shape Model; Liebe, Leonardis, Schiele; ECCV 2004 (JK)
Oct 1   Region Based Models (JK)
  1. Sparselet models for efficient multi-class object detection; H. Oh Song et at, ECCV 2012
  2. Detecting People Using Mutually Consistent Poselet Activations L. Bourdev, S. Maji, T. Brox and J. Malik, ECCV 2010
  3. TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation; J. Shotton, J. Winn, C. Rother, A. Criminisi.
  4. Shared features for multiclass object detection; A. Torralba, K. P. Murphy, W. T. Freeman.
  5. Bottom Up Segmentation slides.pdf (JK)
Oct 8   Region Based Models (JK)
  1. Learning Collections of Part Models for Object Recognition I. Endres, K. Shih, J. Jiaa, and D. Hoiem, CVPR 2013
  2. Part Discovery from Partial Correspondence, S. Maji G. Shakhnarovich, CVPR 2013
  3. Learning to Detect Natural Image Boundaries Using Local Brightness, Color and Texture Cues" David Martin, Charless Fowlkes and Jitendra Malik, IEEE PAMI, 530-549, May 2004.
  4. Segmentation of Natural Images by Texture and BoundaryCompression H. Mobahi, S. R. Rao, A. Y. Yang, S. Sastry, Y. Ma (code available)
  5. Efficient Closed-Form Solution to Generalized Boundary Detection.M. Leordeanu, R. Sukthankar, and C. Sminchisescu; ECCV 2012 (code available)
  6. From Countours to Regions: Empirical Evaluation; P. Arbelaez1, M. Maire, C. Fowlkes and J. Malik
  7. Category Independent Object Proposals I. Endres and D. Hoiem ECCV 2010
  8. Semantic Segmentation slides.pdf (JK)
Oct 15   Columbus Day Break
Oct 22   Categorization, Detection, Parsing continued
  1. Recognition using Regions; Chunhui Gu, Joseph J. Lim, Pablo Arbelaez, Jitendra Malik. CVPR 2009, Miami, Florida. (JK)
  2. E. Borenstein, S. Ulman, Class-specific, top-down segmentation, ECCV 2002
  3. Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images; Saurabh Gupta, Pablo Arbelaez, and Jitendra Malik, CVPR 2013
  4. MRF's, CRF's (JK)
Oct 29   Exemplar Based Methods, Context
  1. Beyond Categories: The Visual Memex Model for Reasoning about Object Relationships. T. Malisiewicz and A. Efros (JK)
  2. Geometric Context from Single Image; D. Hoeim and A. Efros; ICCV 2005 (JK)
  3. Contextual Priming for Object Detection; A. Torralba; IJCV 2003 (JK)
  4. Bottom-up Segmentation and Top Down Detection; S. Fidler, R. Mottaghi, A. Yuille and R. Urtasun
  5. J. Carreira, R. Caseiroa, J. Batista, and C. Sminchisescu. Semantic segmentation with second-order pooling. In ECCV, 2012.
  6. L. Ladicky, P. Sturgess, K. Alahari, C. Russell, and P. H. Torr. What, where and how many? combining object detectors and CRFS.
Nov 5 Attributes, Phrases, Context
    Introduction to Attributes, Phrases, Context Semantic Segmentation slides.pdf (JK)
  1. SuperParsing: Scalable Nonparametric Image Parsing with Superpixels; J. Tighe and S. Lazebnik; ECCV 10, Finding Things: Image Parsing with Regions and Per-Exemplar Detectors J. Tighe and S. Lazebnik, CVPR 2013
  2. Ensemble of Exemplar-SVMs for Object Detection and Beyond Tomasz Malisiewicz, Abhinav Gupta and Alexei A. Efros; Recognition by Association via Learning Per-exemplar Distances Tomasz Malisiewicz and Alexei A. Efros
  3. Extracting Subimages of an Unknown Category from a Set of Images; S. Todorovic, N. Ahuja CVPR 2006
  4. Object Categorization using Co-Occurence, Location and Appearance; C. Galleguilos et. al, overview paper
Nov 12   Structured SVM's, Latent SVM's (JK)
  1. Learning to detect unseen object classes by between-class attribute transfer; C. Lampert et al, CVPR 2009
  2. Describing Objects by their Attributes Ali Farhadi, Ian Endres, Derek Hoiem, David Forsyth, CVPR 2009
  3. Relative Attributes; Devi Parikh and K. Grauman, ICCV 11
  4. Recognition Using Visual Phrases, Ali Farhadi, Amin Sadeghi CVPR 2011.
  5. Attribute Based Object Identification; Y. Sun, L. Bo; D. Fox
Nov 19   Saliency, Search, Scalability, Action Recognition
  1. B. Alexe, T. Deselaers, and V. Ferrari What is an object?, CVPR 2010
  2. Model of saliency based visual attention for rapid scene analysis; Itti, Koch PAMI 1998
  3. A. Prest, C. Schmid, and V. Ferrari Weakly supervised learning of interactions between humans and objects; IEEE PAMI, March 2012.
  4. Hedvig Kjellstrom, Javier Romero, David Martinez and Danica Kragic. Simultaneous visual recognition of manipulation actions and manipulated objects. ECCV, 2008.
  5. Learning to Recognize Objects in Egocentric Activities. Alireza Fathi, Xiaofeng Ren and Jim Rehg, at CVPR 2011.
  6. Understanding Egocentric Accivities Alireza Fathi, Ali Farhadi,James Rehg, ICCV 2011
Nov 26   Domain Adaptation, Active Learning   Weakly-Supervised learning, Fine-Grained Categorization
 
  1. Segmentation as Selective Search for Object Recognition; Koen van de Sande et al., ICCV 2011
  2. Learning to Share Visual Appearance for Multiclass Object Detection; R. Salakhutdinov, A. Torralba, J. Tenenbaum, CVPR 2011
  3. Joint learning of visual attributes, object classes and visual saliency; G. Wang, D. Forsyth, ICCV 2009
  4. Adapting Visual Category Models to New Domains; K. Saenko, B. Kulis, M. Fritz and T. Darrell, ECCV 2010
  5. Discovering Localized Attributes for Fine-Grained Recognition, K. Dua, D. Parikh, D. Crandall, K. Graumann
  6. Simultaneous Active Learning of Classifiers - Attributes via Relative Feedback A. Biswas, D. Parikh
  7. A Codebook-Free and Annotation-Free Approach for Fine-Grained Image Categorization, B. Yao, G. Bradski , Fei-Fei Li
  8. J. Donahue, J. Hoffman, E. Rodner, K. Saenko, T. Darrell, Semi-Supervised Domain Adaptation with Instance Constraints, CVPR 2013

Dec 3   Images and Text, Pictures of People, Applications   Large Databases, Taxonomies, Deep Models
  1. BabyTalk: Understanding and Generating Simple Image Descriptions Girish Kulkarni, Visruth Premraj, Vicente Ordonez, Sagnik Dhar, Siming Li, Yejin Choi, Alexander C. Berg, Tamara L Berg
  2. Im2Text: Describing Images Using 1 Million Captioned Photographs Vicente Ordonez,, Girish Kulkarni,, Tamara L. Berg Neural Information Processing Systems (NIPS), 2011.
  3. Names and Faces; Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire et. al.
  4. A Joint Model of Language and Perception for Grounded Attribute Learning C. Matuszek, N. FitzGerald, L. Zettlemoyer, L. Bo, D. Fox, ICML2012.
  5. Learning to Parse Natural Language Commands to a Robot Control System C. Matuszek, E. Herbst, L. Zettlemoyer, D. Fox, International Symposium on Experimental Robotics (ISER), 2012.
Dec 10   Final Project Presentation slides (.pdf)
  formatting instructions latex (.tar.gz) MS word (.doc)


Related Computer Vision Textbooks
[1] Invitation to 3D Vision: From Images to Geometric Models: Y. Ma, S. Soatto, J. Kosecka and S. Sastry web site
[2] Computer Vision: A Modern Approach: D. Forsythe and J. Ponce, Prentice-Hall, 2003
[3] Image Processing, Analysis, and Machine Vision. Sonka, Hlavac, and Boyle. Thomson.
[4] Computer Vision. Ballard and Brown web site
[5] Computer Vision: Algorithms and Applications. R. Szeliski, 2010, Springer online version of the book
Online Resources
[6] Computer Vision Compendium CVonline
[1] More code details from [1] are here
[7] Fundamentals on image processing (.pdf)
sample images
sample code