Date  Presenter  Description 
1/3/2007  David Bradley 
Today I will be presenting a short overview of several papers from NIPS
06. They are:
Randomized Clustering Forests for Building Fast and Discriminative
Visual Vocabularies
Image Retrieval and Recognition Using Local Distance Functions
MultiTask Feature Learning
Boosting Structured Prediction for Imitation Learning 
1/10/2007  Caroline Pantofaru  NIPS Overview 
1/17/2007  Marius Leordeanu 
Learning to Model Spatial Dependency: SemiSupervised Discriminative Random Fields from NIPS 06, by ChiHoon Lee et all with the background paper:
Semi supervised conditional random fields for improved sequence
segmentation and labeling and another background paper:
SemiSupervised Learning by Entropy Minimization 
1/24/2007
Slides 
Andrew Stein 
I'll focus on the following paper, which won an Outstanding Student Paper Award at the most recent NIPS conference:
Analysis of Contour Motions, In addition, I will likely draw on the following papers, which are also related to motion of boundaries and occlusion events: by Bayerl, P. & Neumann, H., in IJCV, April 2007. by Josh McDermott, Yair Weiss, and Edward H. Adelson, in Perception 2001. 
1/31/2007  Tom Stepleton 
This Wednesday I'll be presenting a tutorial introduction to Dirichlet
Process Mixture Models (DPMs), the flexible, nonparametric Bayesian method
for clustering with variable numbers of clusters (among other things).
I'll introduce a number of terms and metaphors people use to discuss DPMs,
and I'll derive the socalled Chinese Restaurant Process, the Markov Chain
Monte Carlo method for DPM inference. Finally, I'll describe one or two
applications to computer vision, including recent work that integrates
DPMs and MRFs for smooth image segmentation.
This talk comes with a guarantee: once it's done, you'll be able to go back to your office or cube and implement a Dirichlet Process Mixture Model on your ownor your money back! I will cover topics from some of the following papersthe first is a terrific reference, and the rest can serve as a "seed bibliography" on the subject: 
2/7/2007  Ranjith Unnikrishnan 
This week, I'll attempt a tutorial on Fields of Experts (Roth & Black), a framework for learning expressive image priors through largeneighborhood MRFs. I'll describe a recent (ICML '06) extension to multichannel images, and briefly cover their applications in image denoising, inpainting, and optical flow computation.
The talk will draw from the following papers (listed in reverse chronological order): 
2/14/2007  Jiang Ni 
Learning Bayesian networks from data: an informationtheory based approach,
Jie Cheng, Russell Greiner, Jonathan Kelly, David Bell, Weiru
Liu, The Artificial Intelligence Journal, Volume 137, Pages 4390, 2002.
This paper provides constraintbased algorithms for learning Bayesian network structures from data, that require only polynomial numbers of conditional independence (CI) tests. The exponential complexity on the number of CI tests is avoided by using some nice heuristics. 
2/21/2007  James Hays  (nonpublic paper  see email) 
2/28/2007  Fernando de la Torre  CVPR Submissions  see email. 
3/7/2007  Yan Ke 
I'll be presenting some recent work in shape classification. In particular,
I'll be presenting the following three papers:
Siddharth Manay, Daniel Cremers, ByungWoo Hong, Anthony J. Yezzi Jr., and Stefano Soatto. PAMI Oct '06. Lena Gorelick, Meirav Galun, Eitan Sharon, Ronen Basri, and Achi Brandt. PAMI Dec '06. Haibin Ling, and David W. Jacobs. PAMI Feb '07. 
3/14/2007
Slides 
Derek Hoiem 
I will summarize the recent computational theories of human attentional
vision in static scenes. Topics covered: basic physiology and visual
mechanisms, bottomup attention (saliency), and topdown attention
(purposeful search). I will also show a couple attention/changeblindness
video demos. Links to two representative papers are below:

3/21/2007  Brian Potetz 
Paper will be sent via email this week. Please do not redistribute!
Abstract: Belief propagation over pairwise connected Markov Random Fields has become a widely used approach, and has been successfully applied to several important computer vision problems. However, pairwise interactions are often insufficient to capture the full statistics of the problem. Higherorder interactions are sometimes required. Unfortunately, the complexity of belief propagation is exponential in the size of the largest clique. In this paper, we introduce a new technique to compute belief propagation messages in time linear with respect to clique size for a large class of potential functions over realvalued variables. We demonstrate this technique in two applications. First, we perform efficient inference in graphical models where the spatial prior of natural images is captured by 2x2 cliques. This approach shows significant improvement over the commonly used pairwiseconnected models, and may benefit a variety of applications using belief propagation to infer images or range images. Finally, we apply these techniques to shapefromshading and demonstrate significant improvement over previous methods, both in quality and in flexibility. 
3/28/2007  Alyosha Efros  See email for details and papers. Please do not post or link to the distributed papers. 
4/4/2007  Jon Huang 
I'll do an introduction to Gaussian Processes and go over
the following papers which use the Gaussian Process Latent
Variable Model:
Gaussian Process Latent Variable Models for Visualisation of High
Dimensional Data
WiFiSLAM Using Gaussian Process Latent Variable Models
Gaussian Process Dynamical Models
3D People Tracking with Gaussian Process Dynamical Models 
4/11/2007  Henry Kang  See email for details. Please do not distribute the paper. 
4/18/2007  Sanjeev Koppal  I will be presenting Imagebased Material Editing 
4/25/2007  Ankur Datta 
I will be presenting the following CVPR'07 oral paper:
Inferring Temporal Order of Images From 3D Structure
Abstract: 
5/2/2007
Slides (PDF) 
JeanFrancois Lalonde 
I'll be talking about a paper accepted at CVPR 2007, titled "Learning
Color Names from RealWorld Images", by Joost van de Weijer, Cordelia
Schmid and Jakob Verbeek at INRIA RhonesAlpes.
The paper will be distributed by email. Please do not redistribute!
Abstract: 
5/9/2007
Slides 
Tomasz Malisiewicz 
I will be giving a short overview of Supervised Distance Metric Learning techniques as well as discussing the following paper, Image Retrieval and Recognition Using Local Distance Functions. A. Frome, Y. Singer, J. Malik. Proceedings of Neural Information Processing Systems (NIPS) 2006
Abstract: 
5/16/2007
Slides 
Stano Funiak 
I will discuss the following paper from the upcoming CVPR:
Approximate Nearest Subspace Search with Applications to Pattern Recognition
Abstract: 
5/23/2007  No Meeting  Meeting cancelled for Black Friday. Mohit will give this talk on July 11 instead. 
5/30/2007 through 6/20/2007 
No Meeting  Due to so many people being away, plus CVPR, there will be no meetings for a few weeks. 
6/27/2007  Everyone  Special CVPR Overview Meeting organized by Alyosha. 
7/4/2007  July 4th Holiday  No meeting. 
7/11/2007  Postponed  Postponed til next week. 
7/18/2007  Pete Barnum 
In many cases, computer vision focuses on pictures taken with unknown camera parameters.
We've also seen cases where the camera is modified to capture additional information,
such as with a modulated shutter. In my talk, I will discuss a few papers that go even further,
and attempt to use feedback loops to optimize the camera settings during acquisition.
I'll discuss parts of these three papers (not the hardware, except for the basic theory): Marc P. Christensen et al. Applied Optics 45(13) May 2006 Shree K. Nayar, Vlad Branzoi, and Terry E. Boult CVPR 2004 Cha Zhang and Tsuhan Chen ICIP 2004 And if you're especially interested, you can also look at: J. Castracane and M. Gutin Diffractive and Holographic Technologies, Systems, and Spatial Light Modulators IV 1999 Marc P. Christensen, et al. Applied Optics 41(29) October 2002 
7/25/2007  Mohit Gupta 
I will be presenting the following paper from ECCV 2006:
Confocal Stereo
(Project Page) This paper got the LonguetHiggins Best Paper Award, Honorable Mention.
Abstract: 
8/1/2007  David Bradley 
One of the great strengths of the human visual system is
it's ability to share common hardware across many different tasks,
and to learn from just a few labeled examples for each task.
I will present a survey of multitask learning algorithms that attempt
to replicate that ability to share computation, and labeled data among a
group of tasks, and describe how they are being used in vision applications.
The papers I will talk about include:

8/8/2007  Christopher Geyer 
I am interested in largescale data association problems, and on Wednesday I will talk about the following papers:
First: Abstract: Tracking posteriors estimates for problems with data association uncertainty is one of the big open problems in the literature on filtering and tracking. This paper presents a new filter for online tracking of many individual objects with data association ambiguities. It tightly integrates the continuous aspects of the problem  locating the objects  with the discrete aspects  the data association ambiguity. The key innovation is a probabilistic information matrix that efficiently does identity management, that is, it links entities with internal tracks of the filter, enabling it to maintain a full posterior over the system amid data association uncertainties. The filter scales quadratically in complexity, just like a conventional Kalman filter. We derive the algorithm formally and present largescale results.
Second, if I get to it: 
8/15/2007  Marius Leordeanu 
I am thinking of talking about the following papers, not sure which one
will be the main focus:
1. A. Hoogs, R. Collins, B. Kaucic and J. Mundy. A Common Set of Perceptual Observables for Grouping, FigureGround Discrimination and Texture Classification. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Special Section on Perceptual Organization in Computer Vision, 25(4) 2. Learning to segment images using regionbased perceptual features, Kaufhold, J. Hoogs, A., CVPR 2004 3. Supervised learning of large perceptual organization: graph spectral partitioning and learning automata, Sarkar, S.; Soundararajan, P., PAMI 2000, vol 22, no 5. 
8/22/2007  Caroline Pantofaru 
Using HighLevel Visual Information for Color Constancy Joost van de Weijer, Cordelia Schmid, Jakob Verbeek We propose to use highlevel visual information to improve illuminant estimation. Several illuminant estimation approaches are applied to compute a set of possible illuminants. For each of them an illuminant color corrected image is evaluated on the likelihood of its semantic content: is the grass green, the road grey, and the sky blue, in correspondence with our prior knowledge of the world. The illuminant resulting in the most likely semantic composition of the image is selected as the illuminant color. To evaluate the likelihood of the semantic content, we apply probabilistic latent semantic analysis. The image is modelled as a mixture of semantic classes, such as sky, grass, road, and building. The class description is based on texture, position and color information. Experiments show that the use of highlevel information improves illuminant estimation over a purely bottomup approach. Furthermore, the proposed method is shown to significantly improve semantic class recognition performance. 
8/29/2007  Ranjith Unnikrishnan 
This week, I'll survey the Perspective nPoint (PnP) problem, stated as:
Given n correspondences between 3D points in world coordinates and their
2D projections in a calibrated camera, find the rigid transform relating
the world and camera frames.
The highlight will be a ICCV '07 paper [1] that uses a clever and simple math trick to give a noniterative O(n) solution to the problem, as or more accurate than stateoftheart methods that are O(n^5) or more! This should be of particular interest to people doing sensor calibration, and modelbased pose estimation and tracking. [1] Accurate Noniterative O(n) solution to the PnP problem, F.MorenoNoguer, V.Lepetit and P.Fua, ICCV '07 preprint
and it's closest competitor: 
9/5/2007  Cancelled  Cancelled in favor of Special VASC Seminar. 
9/12/2007  Jiang Ni  I will talk about my research: Face View Synthesis Using A Single Image. Face view synthesis involves using one view of a face to artificially render another view. The fact that the input is only a single image, makes the problem very difficult. We observe that the statistical dependency varies among different groupings of pixels in the 2D images and use a Bayesian Network to represent such a sparse structure. This is an ongoing research so your feedback or discussion are welcome. Here is a related work by Vetter if you are interested. 
9/19/2007  Gunhee Kim 
I'm thinking of presenting two papers from ETH Zurich which apply data
mining techniques to computer vision problems  Recognition and Video
Mining.
One is a ICCV 2007 Paper:
The other is: 
9/26/2007 
Fernando de la Torre 
***Note special location this week: NSH 1507 (still 4:00)***
Learning Graph Matching, Tiberio Caetano, Li Cheng, Quoc Le, Alex Smola, ICCV 2007. 
10/3/2007 AT 4:30! 
Yan Ke 
*** Note that we're switching to a 4:30 start time! ***
I'll be giving a practice job talk about my work in using volumetric features for event detection. It's based on the following papers:
Abstract: 
10/10/2007  James Hays  TBA 
10/17/2007  No Meeting  ICCV  Meeting Cancelled. 
10/24/2007  No Meeting  Intel Open House. ICCV Overview postponed to next week. 
10/31/2007  Alyosha Efros  ICCV Overview 
11/7/2007  Pete Barnum 
Inverse Shade Trees for NonParametric Material Representation and
Editing, by Jason Lawrence, Aner BenArtzi, Christopher DeCoro, Wojciech
Matusik, Hanspeter Psterr, Ravi Ramamoorthi, and Szymon Rusinkiewicz.
SIGGRAPH 2006
AppWand: Editing Measured Materials using AppearanceDriven Optimization, by Fabio Pellacini and Jason Lawrence. SIGGRAPH 2007 
11/14/2007  Tom Stepleton 
This meeting has been cancelled. Tom will give his talk on a later date.
3D generic object categorization, localization, and pose estimation This paper is about building 3D partbased models of object categories. An object is comprised of a collection of 2D "canonical part" images (e.g. a car's bumper) linked to each other through coordinate transforms: imagine arranging polaroids of object parts on a sphere surrounding the object. The technique learns the model of a class in an unsupervised way from still images of instances of the class. I like this model because I think the brain represents objects in a similar way, and if I have time to prepare the information I might say something about that. 
11/21/2007  Thanksgiving  No meeting. 
11/28/2007  Yaser Sheikh 
I'll be presenting a recent paper of mine from CVPR 2007: Spacetime Geometry of Gallilean Cameras A projection model is presented for cameras moving at constant velocity (which we refer to as Galilean cameras). We introduce the concept of spacetime projection and show that perspective imaging and linear pushbroom imaging are specializations of the proposed model. The epipolar geometry between two such cameras is developed and we derive the Galilean fundamental matrix. We show how six different "fundamental" matrices can be directly recovered from the Galilean fundamental matrix including the classic fundamental matrix, the Linear Pushbroom fundamental matrix and a fundamental matrix relating Epipolar Plane Images. To estimate the parameters of this fundamental matrix and the mapping between videos in the case of planar scenes we describe linear algorithms and report experimental performance of these algorithms. 
12/5/2007  Andrew Stein  Due to the CVPR extension, there will be no meeting today. 
12/12/2007  Everyone  "CVPR Decompression Fest" 