Course program Week 1 Section Introduction to recognition and indexing of visual data

(Professor: Alberto del Bimbo)

(Professor: Alberto del Bimbo)

• 
  Global image features : Color; Texture; Edges and Lines
  
• 
  Dimensionality reduction: PCA, LDA, Eigenfaces
  

[A] Richard Szeliski, Computer Vision Algorithms and Applications, Springer 2010, Chapter 4

[B] Alberto del Bimbo, Visual Information Retrieval, Morgan Khaufman, 1999, Chapter 2-4
Week 3

Section 3. The MPEG7 standard

(Professor: Alberto del Bimbo)

• 
  MPEG7 holistic descriptors [1]
  

[1] ISO/IEC TR 15938-8:2002, Information technology -- Multimedia content description interface-Part 8: Extraction and use of MPEG-7 descriptions, http://www.iso.org/iso/

(Assistant: Marco Bertini)

(Professor: Alberto del Bimbo)

• 
  Rotation invariant Harris corner detector
  
• 
  Scale invariant keypoint detectors: Harris-Laplacian [1], SIFT Scale Invariant Feature Transform [2], SURF Speed Up Robust Features [3]
  
• 
  Affine invariant region detectors: Harris affine, Intensity Extrema Regions, MSER Maximally Stable Extremal Regions [4]
  
• 
  Local descriptors: SIFT [2], Color SIFT, SURF [3], GLOH Gradient Location and Orientation Histogram
  
• 
  References
  

[1] Krystian Mikolajczyk and Cordelia Schmid, A Performance Evaluation of Local Descriptors, IEEE TPAMI 2005

[2] David Lowe, Distinctive Image Features from Scale-Invariant Keypoints , International Journal of Computer Vision, 2004.

[3] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool, Speeded-Up Robust Features (SURF), Elsevier, 2008

[4] J. Matas, O. Chum, M. Urban, T. Pajdla, Robust Wide Baseline Stereo from Maximally Stable Extremal Regions, British Machine Vision Int. Conference, 2002

Week 7

Section 5 Visual words and bag of Words representation

(Professor: Alberto del Bimbo)

• 
  Visual Words and Bag of Words model: vocabulary formation by K-means, Radius-based clustering [1]
  

[A] Richard Szeliski, Computer Vision Algorithms and Applications, Springer 2010, Chapter 14

[1] Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, Cédric Bray , Visual Categorization with Bags of Keypoints
Week 8

Section 6. Object instance recognition

(Professor: Alberto del Bimbo)

• 
  Distance measures
  

• 
  Nearest Neighbour Matching
  
• 
  Geometric alignment and outliers rejection: Random Sample Consensus
  
• 
  Video Google [1]
  

[A] Richard Szeliski, Computer Vision Algorithms and Applications, Springer 2010, Chapter 4, 5, 6

[1] Josef Sivic, Andrew Zisserman, Video Google: A Text Retrieval Approach to Object Matching in Videos, ICCV 2003
Week 9 - 10

Section 7. Object categorization

(Professors: Alberto del Bimbo, Andy Bagdanov°, Lorenzo Seidenari*)

• 
  Bayes classification (Recall of statistical principles) °
  
• 
  Support Vector Machines discriminative classifier °
  
• 
  Partial matching of sets of features: Pyramid Matching Kernel [1] Spatial Pyramid Matching
  
• 
  HOG Histogram of Oriented Gradients people detector [2]
  
• 
  Boosting classifier, Adaboost
  
• 
  Viola and Jones face detector [3]
  
• 
  Probabilistic Latent Semantic Analysis generative classifier [4] *
  
• 
  Expectation maximization (Recall of statistical principles) *
  

[A] Richard Szeliski, Computer Vision Algorithms and Applications, Springer 2010, Chapter 4, 5, 6

[B] Christopher Bishop, Pattern Recognition and Machine Learning, Springer 2006, Chapter 2

[1] Kristen Grauman and Trevor Darrell, Pyramid Match Kernels: Discriminative Classification with Sets of Image Features, IEEE ICCV 2005

[2] Navneet Dalal and Bill Triggs, Histograms of Oriented Gradients for Human Detection, IEEE CVPR Int. Conference 2005

[3] Paul Viola and Michael Jones, Robust Real-time Object Detection , Int. Wkshop on Statistical and Computational Theories of Vision, 2001

[4] Florent Monay, Daniel Gatica-Perez, PLSA-based Image Auto-Annotation: Constraining the Latent Space, ACM Multimedia 2004
Week 11

Laboratory 2 : Bag of Visual Words

(Assistants: Marco Bertini, Lamberto Ballan, Lorenzo Seidenari)

(Professors: Lorenzo Seidenari °, Andy Bagdanov*)

• 
  Spatio-temporal features: holistic features; local features: STIP Spatio-Temporal Interest Point
  

• 
  Action and Event recognition [2] °
  

• 
  Detection in video sequences *
  

[1] Ivan Laptev, On Space-Time Interest Points, International Journal of Computer Vision, 2005

[2] L. Ballan, M. Bertini, A. Del Bimbo, L. Seidenari, and G. Serra, "Effective Codebooks for Human Action Categorization," IEEE ICCV Int. Workshop on Video-oriented Object and Event Classification (VOEC), 2009.
Week 13

Laboratory 3 : Detection and tracking

(Assistants: Andy Bagdanov, Giuseppe Lisanti)

(Professor: Alberto del Bimbo)

• 
  Vocabulary Tree [1]
  
• 
  Multidimensional hashing: Local Sensitive Hashing, Pyramid Match Hashing, Semantic
  

• 
  Performance measures
  

[A] Richard Szeliski, Computer Vision Algorithms and Applications, Springer 2010, Chapter 14

[4] David Nister and Henrik Stewenius, Scalable Recognition with a Vocabulary Tree, IEEE CVPR Int. Conference, 2006

[2] Aristides Gionis, Piotr Indyky, Rajeev Motwaniz, Similarity Search in High Dimensions via Hashing, IEEE VLDB, Int. Conference 1999

[3] Brian Kulis Kristen Grauman, Kernelized Locality-Sensitive Hashing for Scalable Image Search, IEEE ICCV int. Conference, 2009

[4] Mohamed Aly, Peter Welinder, Mario Munich, Pietro Perona, Scaling Object Recognition: Benchmark of Current State of the Art Techniques, IEEE ICCV Int. Conference, 2009

• 
  Wordnet and ontologies [1] °
  
• 
  RDF, OWL, SWRL °
  
• 
  Data from Social Networks *
  

[1] John Davies, Dieter Fensel, Frank van Harmelen, Towards the Semantic Web: Ontology-driven Knowledge Management, 2002

(password protected)

Free copy downloadable at: http://szeliski.org/Book/