Year 2004 (in chronological order)
Date  Presenter  Description 
1/21/2004

Andrew Stein 
I've selected the following two papers to discuss at next week's group
meeting. They are both from the most recent ICCV. They are somewhat
related in that each incorporates temporal information to extract
information (find features / do classification) from image sequences. Both
are also essentially extensions to the temporal domain of formerly
spatialonly methodologies, so I thought that was another connection.
Spacetime Interest Points by Ivan Laptev and Tony Lindeberg. Paper here. Detecting Pedestrians Using Patterns of Motion and Appearance by Paul Viola, Michael Jones, and Daniel Snow . 2003 Marr Prize Winner. Paper here. 
1/28/2004

Tal Blum 
I will be presenting the papers:

2/04/2004

Yan Ke 
I'll be presenting my recent work on local image descriptors.
We extend David Lowe's SIFT by applying PCA to build the descriptor
instead of using windows of histograms.
A technical report can be found here.

2/11/2004

Fernando De La Torre 
The papers I will discuss on wednesday are:
Extreme Components Analysis and if I have time: Nonlinear CCA and PCA by Alignment of Local Models, Paper here. Enjoy the reading. 
2/18/2004

Sanjiv Kumar 
I will talk about the paper from Teh
and Welling about generalized inference:
The Unified Propagation and Scaling Algorithm, Y. W. Teh and M. Welling, NIPS 2001. Paper here. 
2/25/2004

Ranjith Unnikrishnan 
I'll be presenting Outofsample extensions for LLE, Isomap, MDS,
Eigenmaps and Spectral clustering by Y.Bengio et al (NIPS 2003).
Paper here.
The paper develops a unified framework for the above manifold learning algorithms and extensions for outofsample data. A more detailed tech report is Spectral Clustering and Kernel PCA are Learning Eigenfunctions. Paper here.

3/3/2004

Caroline Pantofaru 
I'll be talking about Unsupervised Improvement of Visual Detectors using Co Training by A Levin, P Viola, and Y Freund, from ICCV 2003. You can find the paper here or here.

3/10/2004

No Meeting (Spring Break) 
3/17/2004

Tom Stepleton 
At this week's misc reading group meeting, I'll be presenting Tony
Jebara's ICCV 2003 paper, Images as Bags of Pixels. You can download the
paper here.
Bags of Pixels is a technique for representing images as unordered sets of tuples. Finding optimal orderings for these tuples across sets of images automatically estimates pixel correspondences over the images and compacts the image representations into a subspace conducive to PCA. Furthermore, resultant PCA basis vectors have visual characteristics that give rise to compelling intuitive interpretations. This technique can also be supplied to other sampled data, like audio recordings. For more background, you may also wish to take a look at this paper, which describes the convex optimization technique of the Bags of Pixels paper in slightly greater detail. 
3/24/2004

Jiang Ni 
I will be presenting Portilla & Simoncelli's IJCV 2000 paper on texture synthesis usnig a parametric statistical model: A parametric texture model based on joint statistics of complex wavelet coefficients Paper here.
And if I have time, I may also talk about Wei & Levoy's Siggraph 2000 paper on texture synthesis using a nonparametric model: 
3/31/2004

Derek Hoiem 
I'm presenting an overview/tutorial presentation on Adaboost
(the vote was 321 adaboostbayes netsunlabeled data). I'll give some background,
cover the basic adaboost algorithms, present some theoretical results, discuss practical
issues such as the complexity of the weak learner and noisy data, and talk about some
of the Adaboost variants. I'll be focusing on confidenceweighted adaboost in the
twoclass case. Recommended reading is one of the following that can all be found
here.
Robert E. Schapire.
Jerome Friedman, Trevor Hastie and Robert Tibshirani.
Robert E. Schapire and Yoram Singer. 
4/7/2004

Owen Carmichael 
This MISC reading group meeting will be an overview of the
medical image analysis work I have been involved with since getting my
PhD in September. There are no papers to read and little in the way of
experimental results since I have only been at it for 6 months. The
general problem is, "In what way can images of the brain help us to
detect Alzheimer's Disease earlier than we are detecting it now?" The
specific computer vision and statistics issues are:
1. Automatically generating 3D models of lowcontrast brain structures
from volumetric images. I will also touch on a couple of featurebased registration projects that I am helping to give advise to. 
4/14/2004

David Tolliver  As has become my habit I'll present another paper by Lior Wolf and Amnon Sha'shua. I'll describe their Qalpha algorithm, and present results from their recent ECCV 2004 paper. 
4/21/2004

Bart Nabbe 
From Alexei's web page:
Texture Synthesis In our 1999 work ([Efros and Leung,'99]) we tried to address this shortcoming by proposing a very different and extremely simple way of synthesizing textures locally, onepixelatatime. In recent years this algorithm has been used for synthesiszing a large spectrum of textures as well as filling holes in textured regions. In our latest work ([Efros and Freeman,'01]) we show that similarly good results can be obtained by an even simpler (and much faster) procedure of quilting together patches of the input texutre. Moreover, we demonstrate a method of transfering texture from one object onto another (e.g. rendering a man's face with rice). 
4/28/2004

Martial Hebert  I'll discuss the Brendan Frey paper on Epitomic Analysis (paper here) at the Wed. meeting. I can't remember exactly why I liked it. 
5/5/2004

James Hays  I will discuss the recent texture synthesis work of Yanxi Liu, Steve Lin, and myself. Our work concerns nearregular textures  textures made of up repeated but not necessarily identical texture elements. This is a class of textures that general texture synthesis algorithms, from Efros and Leung to Graph Cuts, do not handle well. We model the different ways textures depart from regular tilings with Geometry, Lighting, and Color deformation fields. We use these deformation fields to manipulate the textures in interesting ways. A preprint of the paper, to appear in SIGGRAPH 2004, can be found here. 
5/12/2004

Black Friday  No Meeting Today (postponed until May 26). 
5/19/2004

Dennis Strelow 
I'll give a highlevel overview of my thesis research since the last
time I presented my work to the MISC group, which includes
work on 6 DOF motion estimation from image measurements and measurements
from inexpensive inertial sensors; and the "smalls" image feature
tracker for shapefrommotion and similar applications. I'll include
motion estimation results from data taken during the Hyperion rover's
first field test in 2003 and from CMU's wide area crane.
I'll try to present so that no reading is required beforehand. If you can't wait, there is a brief discussion of 6 DOF motion from image and inertial measurements here and a much more detailed discussion, which includes the Hyperion results, is available here. There's no paper describing the smalls tracker at this point. 
5/26/2004

Marius Leordeanu 
The paper I will present for this week is:
Selective Sampling With Redundant Views 
6/2/2004

Daniel Huber  Practice job talk. 
6/9/2004

Caroline Pantofaru 
I'll be talking about: "Sharing features: efficient boosting procedures for multiclass object detection" by Torralba, Murphy, and Freeman from CVPR 2004
Paper here
And "Mutual Boosting for Contextual Inference" by Michael Fink and Pietro Perona from NIPS 2003 Paper here The main links between the papers are the obvious: boosting and multiclass detection. The main reason that I've listed both of them is because I don't think either one will fill the entire meeting. But then again, you never know. 
6/16/2004

Ranjith Unnikrishnan 
This week I'll try to cover two papers that revisit conventional
clustering techniques:
(1) "Interpreting and Extending Classical Agglomerative Clustering
Algorithms using a ModelBased Approach". In ICML, 2002
Link here , and The first shows how common heuristic clustering algorithms are each equivalent to a hierarchical modelbased method, and offers implementers intuition on how to modify and choose between algorithms / distance measures. The second presents an approach that uses multiple clustering objective functions simultaneously, and tries to find a robust, least conflicting partition of the dataset to be clustered. 
6/23/2004

Tom Stepleton 
For the next Misc Reading Group, I'll be presenting
Weakly Supervised Learning of Visual Models and Its Application to ContentBased Retrieval In this paper, Schmid trains visual models for image retrieval by building up libraries of significant rotationinvariant descriptors from positive and negative class examples. Aside from this binary labeling, no other handholding is performed. A local link to the paper can be found here. 
6/30/2004

CVPR  No Meeting  TBA 
7/7/2004

Owen Carmichael 
I will discuss a couple of interesting papers I saw at CVPR on
lowdimensional embeddings of highdimensional manifolds of data. I will
start on this one, which I thought was neat because it casts embedding as
a classification problem:
BoostMap: A Method for Efficient Approximate Similarity
Rankings Depending on the time and demand, I might go on to talk about this one by one of the Locally Linear Embedding guys. It won best paper:
Unsupervised Learning of Image Manifolds by Semidefinite
Programming 
7/14/2004

Jiang Ni 
The paper I will be talking about is: Combining Topdown and Bottomup Segmentation, by Borenstein, Sharon and Ullman. Link here This paper was presented at the POCV workshop of CVPR 2004, on June 28 morning. The topdown approach uses prior knowledge about an object to guide the segmentation, whereas the bottomup approach first segments the image into regions and then groups the objectrelated regions together. This paper shows how to combine these two approaches together. 
7/21/2004

Fernando de la Torre 
On Wednesday I will present, A RaoBlackwellized Particle Filter for EigenTracking Paper here Enjoy reading!! 
7/28/2004

Yan Ke 
I'll be presenting my recent work on using locality sensitive hashing
(LSH) to index and search local descriptors for image retrieval.
See this link.
I'll also talk about ongoing work in applying similar techniques to music retrieval. 
8/4/2004

CANCELLED  Conflict with sponsor presentation. 
8/11/2004

Jake Sprouse 
I'll present Multiscale Conditional Random Fields for Image Labeling
by Xuming He, Richard Zemel, and Miguel CarreiraPerpinan from CVPR '04.
Paper here.
The authors encode contextual information using learnt label pattern fields and combine it with lowlevel classification using CRFs. 
8/18/2004

James Hays  TBA 
8/25/2004

Cris Dima 
I will present Estimating Replicability of
Classifier Learning Experiments by Remco Bouckaert (ICML 2004).
An electronic copy can be downloaded
here.
Here is the abstract: Replicability of machine learning experiments measures how likely it is that the outcome of one experiment is repeated when performed with a different randomization of the data. In this paper, we present an estimator of replicability of an experiment that is efficient. More precisely, the estimator is unbiased and has lowest variance in the class of estimators formed by a linear combination of outcomes of experiments on a given data set.We gathered empirical data for comparing experiments consisting of different sampling schemes and hypothesis tests. Both factors are shown to have an impact on replicability of experiments. The data suggests that sign tests should not be used due to low replicability. Ranked sum tests show better performance, but the combination of a sorted runs sampling scheme with a ttest gives the most desirable performance judged on Type I and II error and replicability. 
9/1/2004

Jonas August 
The paper is Descour & Dereniak's
Computedtomography imaging spectrometer in Applied Optics '95.
This paper describes a new way of making hyperspectral images free of motion distortion by combining diffraction gratings with a CTstyle inverse problem formulation. I'll describe this new sensor and outline the computations involved.
The paper was scanned in, so the PDF file is quite large (14MB). 
9/8/2004

Daniel Huber  Survey of ECCV papers. 
9/15/2004

Derek Hoiem 
I will give an overview talk on using context in object
detection. The bulk of work in context can be placed into one of three
categories: saliency (what are likely locations/scales of the object),
local context (neighboring labels are used), and objectbased context
(likelihoods of other objects' locations are used). I will attempt to
organize and summarize the important ideas from about a dozen papers, but I
recommend getting the gist (at least read intro, headings, figures and
conclusions) of the three papers below in preparation for
Wednesday. Incidentally, this presentation will be used to fulfill my
speaking qualifier requirement.
Statistical Context Priming for Object Detection, Torralba, et. al 2001

9/22/2004

James Hays 
Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in ND Images
Yuri Boykov & MariePierre Jolly ICCV 2001 Paper available here. This paper describes an exact, lowpolynomial time solution to finding a MAP labeling for twolabel, Ndimensional Markov Random Fields. This is used for interactive foreground/background extraction, where the labeling of image pixels simply determines whether an object is foreground or background. It has similarly been used for texture synthesis. After discussing this paper we'll talk about its extensions to multiclass problems, and then we'll look at various direct extensions to this paper at SIGGRAPH this year. 
9/29/2004

Goksel Dedeoglu 
TransformationInvariant Embedding for Image Analysis A. Ghodsi, J. Huang, and D. Schuurmans ECCV 2004 
10/6/2004

Sanjiv Kumar 
I will talk about the following work on learning
markov networks from Stanford learning group:
MaxMargin Markov Networks, B. Taskar, C. Guestrin and D. Koller. Neural Information Processing Systems Conference (NIPS03), Vancouver, Canada, December 2003. The paper can be found here. This work is an extension of SVM to structured or relational data (e.g. chains or MRFs). 
10/13/2004

Cancelled  25th Anniversary Robotics Symposium (Schedule here) 
10/20/2004

Bart Nabbe 
Epipolar Geometry from Three Correspondences Chum, Matas, Obdrzalek The paper describes LORANSAC 3LAF – a new algorithm for the correspondence problem; Exploiting processes proposed for computation of affineinvariant local frames, three pointtopoint correspondences are found for each regiontoregion correspondence. Consequently, it is sufficient to select only triplets of region correspondences in the hypothesis stage of epipolar geometry estimation by RANSAC. The paper can be found here. 
10/27/2004

Ting Liu 
This paper concerns approximate nearest neighbor searching algorithms,
which have become increasingly important, especially in high
dimensional perception areas such as computer vision, with dozens of
publications in recent years. Much of this enthusiasm is due to a
successful new approximate nearest neighbor approach called Locality
Sensitive Hashing (LSH). In this paper we ask the question: can
earlier spatial data structure approaches to {\em exact} nearest
neighbor, such as metric trees, be altered to provide approximate
answers to proximity queries and if so, how? We introduce a new kind
of metric tree that allows overlap: certain datapoints may appear in
both the children of a parent. We also introduce new approximate kNN
search algorithms on this structure. We show why these structures
should be able to exploit the same randomprojectionbased
approximations that LSH enjoys, but with a simpler algorithm and
perhaps with greater efficiency. We then provide a detailed empirical
evaluation on five large, high dimensional datasets which show
accelerations one to three orders of magnitude
over LSH. This result holds
true throughout the spectrum of approximation levels.
The following papers are all related to this talk: 
11/3/2004

Alyosha Efros 
Seeing Through Water
Abstract: Joint work with Volkan Isler, Jianbo Shi and Mirko Visontai. Accepted to NIPS'04, draft can be found here. 
11/10/2004

Srinivasa Narasimhan 
I will be presenting the recent CVPR paper which won an award:
Programmable Imaging using a Digital Micromirror Array The paper can be found here. I will also try to discuss the different sensors built at Columbia on dynamic range. 
11/17/2004

Andrew Stein 
Scaleinvariant shape features for recognition of object categories Frederic Jurie and Cordelia Schmid CVPR 2004
Abstract: The paper can be found here. (If that link doesn't work for some reason, you should be able to search for the paper on IEEE Xplore.)
If there's time  and if my slides are ready  I may also take 1520 minutes to do a practice talk for WACV. This would cover my own work on backgroundinvariant features. 
11/24/2004

Thanksgiving  No Meeting 
12/1/2004

Sanjeev Koppal 
Appearance Sampling for Obtaining A Set of Basis Images
for Variable Illumination Imari Sato, Takahiro Okabe, Yoichi Sato, and Katsushi Ikeuchi Paper here. 
12/8/2004

Qifa Ke 
Learning a kernel matrix for nonlinear dimensionality reduction K. Q. Weinberger, F. Sha, and L. K. Saul ICML 2004 This paper is about how to use semidefinite programming to learn the kernel matrix that can "unfold" the manifold when it maps the input into the feature space. (The input highdimensional data is assumed to lie in some lowdimensional manifold). 
12/15/2004

Black "Friday"  No meeting. 
12/22/2004

Winter Break  No meeting. 
12/29/2004

Winter Break  No meeting. 
Last modified: 12/13/2004