Multidimensional Digital Signal Processing

ECG782 Fall 2015

Paper Reading List

• Stauffer and Grimson, "Adaptive background mixture models for real-time tracking", 1998
  Mixture of Gaussian for robust background modeling.
  [pdf]
  Presenter: Brendan Morris Tu. 11/08
  
  
• Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", 1999
  Powerful SIFT feature used for image matching and object detection.
  [pdf] [notes]
  Presenter:
  
  
• Viola and Jones, "Robust Real-time Object Detection", 2001
  Boosted Haar-like cascade for fast object detection. Well suited for rigid objects like faces and vehicles
  [pdf]
  Presenter: Jadin Tredup
  
  
• Dalal and Triggs, "Histogram of Oriented Gradients for Human Detection", 2005
  Basic edge-type feature useful for object detection and recognition. Designed for pedestrian detection.
  [pdf] [notes]
  Presenter:
  
  
• Itti et al., "A model of saliency-based visual attention for rapid scene analysis", 1998
  Biologically inspired feature maps used to detect interesting (salient) image regions.
  [pdf] [notes]
  Presenter:
  
  
• Turk and Pentland, "Eigenfaces for Recognition", 1991
  Simple PCA subspace method for face recognition.
  [pdf] [notes]
  Presenter:
  
  
• Ahonen et al., "Face Description with Local Binary Patterns: Application to Face Recognition", 2006
  Simple texture patterns used for facial recognition.
  [pdf] [draft] [notes]
  Presenter:
  
  
• Maldonado-Bascon et al., "Road-Sign Detection and Recognition Based on Support Vector Machines", 2007
  Use of SVM to very effectively detect road signs.
  [pdf]
  Presenter:
  
  
• Sivic and Zisserman, "Video Google: A Text Retrieval Approach to Object Matching in Videos", 2003
  Bag of visual words for detection and recognition using web text document matching techniques.
  [pdf] [notes]
  Presenter:
  
  
• Makris and Ellis, "Learning semantic scene models from observing activity in visual surveillance", 2005
  Use of tracking information to learn scene context and activity.
  [pdf]
  Presenter:
  
  
• Gupte et al., "Detection and Classification of Vehicles", 2002
  Early vehicle tracking and classification system.
  [pdf]
  Presenter:
  
  
• Blake and Isard, "CONDENSATION - Conditional Density Propagation for Visual Tracking", 1998
  Particle filtering approach for tracking curves in visual clutter.
  [pdf] [notes]
  Presenter:
  
  
• Felzenszwalb et. al, "Object Detection with Discriminatively Trained Part Based Models", 2010
  State-of-the-art object detection. Combines smaller HOG parts for better performance
  [pdf] [notes]
  Presenter:
  
  
• Lazebnik, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories", 2006
  [pdf] [notes]
  Presenter:
  
  
• Belongie et. al, "Shape Matching and Object Recognition Using Shape Contexts", 2001
  Object detection and recognition descriptor based on object shape.
  [pdf] [notes]
  Presenter:
  
  
• Belhumeur et. al, "Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection", 1997
  LDA projection subspace for better face recognition. Extension of Eigenface.
  [pdf] [notes]
  Presenter:
  
  
• McCall and Trivedi, "Video-Based Lane Estimation and Tracking for Driver Assistance: Survey, System, and Evaluation", 2006
  Violet system for robust lane detection for driver assistance systems.
  [pdf]
  Presenter:
  
  
• Shi and Malik, "Normalized Cuts and Image Segmentation", 2000
  Graph-based segmentation using graph cuts and connected with computational efficient spectral clustering. Used for image segmentation.
  [pdf] [notes]
  Presenter:
  
  
• Comaniciu and Meer, "Mean shift: a robust approach toward feature space analysis", 2002
  Iterative probability density estimation and maximization. Used in segmentation and tracking.
  [pdf] [notes]
  Presenter:
  
  
• Girshick, "Fast R-CNN", 2015
  Fast object detection using region proposal and efficient convolutional neural network architecture.
  [pdf]
  Presenter:
  
  
• Razavian et al., "CNN Features off-the-shelf: an Astounding Baseline for Recognition", 2014
  Convolutional neural networks trained on large scale data used as feature selection for other vision tasks.
  [pdf]
  Presenter:
  
  
• Uijlings et al, "Selective Search for Object Recognition", 2013
  Segmentation for object localization.
  [link]
  Presenter: