Browsing CBCL Memos (1993  2004) by Title
Now showing items 7493 of 123

Object Detection in Images by Components
(19990811)In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is ... 
Observations on Cortical Mechanisms for Object Recognition andsLearning
(19931201)This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The viewcentered scheme relies on modules for learning from examples, such as Hyperbflike ... 
On Convergence Properties of the EM Algorithm for Gaussian Mixtures
(19950421)"ExpectationMaximization'' (EM) algorithm and gradientbased approaches for maximum likelihood learning of finite Gaussian mixtures. We show that the EM step in parameter space is obtained from the gradient via a ... 
On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications
(19971201)This paper investigates the linear degeneracies of projective structure estimation from point and line features across three views. We show that the rank of the linear system of equations for recovering the trilinear tensor ... 
On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
(19930801)Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton ... 
On the difficulty of featurebased attentional modulations in visual object recognition: A modeling study.
(20040114)Numerous psychophysical experiments have shown an important role for attentional modulations in vision. Behaviorally, allocation of attention can improve performance in object detection and recognition tasks. At the neural ... 
On the Noise Model of Support Vector Machine Regression
(19981001)Support Vector Machines Regression (SVMR) is a regression technique which has been recently introduced by V. Vapnik and his collaborators (Vapnik, 1995; Vapnik, Golowich and Smola, 1996). In SVMR the goodness of fit ... 
On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces
(19990501)This paper presents a computation of the $V_gamma$ dimension for regression in bounded subspaces of Reproducing Kernel Hilbert Spaces (RKHS) for the Support Vector Machine (SVM) regression $epsilon$insensitive loss function, ... 
People Recognition in Image Sequences by Supervised Learning
(20000601)We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by colorbased and shapebased features. Recognition is carried out through combinations of Support ... 
Perceiving Illumination Inconsistencies in Scenes
(20011105)The human visual system is adept at detecting and encoding statistical regularities in its spatiotemporal environment. Here we report an unexpected failure of this ability in the context of perceiving inconsistencies in ... 
Perceptual Evaluation of VideoRealistic Speech
(20030228)abstract With many visual speech animation techniques now available, there is a clear need for systematic perceptual evaluation schemes. We describe here our scheme and its application to a new videorealistic ... 
Perceptuallybased Comparison of Image Similarity Metrics
(20010701)The image comparison operation ??sessing how well one image matches another ??rms a critical component of many image analysis systems and models of human visual processing. Two norms used commonly for this purpose are L1 ... 
Policy Improvement for POMDPs Using Normalized Importance Sampling
(20010320)We present a new method for estimating the expected return of a POMDP from experience. The estimator does not assume any knowle ge of the POMDP and allows the experience to be gathered with an arbitrary set of policies. ... 
PreAttentive Segmentation in the Primary Visual Cortex
(19980630)Stimuli outside classical receptive fields have been shown to exert significant influence over the activities of neurons in primary visual cortexWe propose that contextual influences are used for preattentive visual ... 
Priors Stabilizers and Basis Functions: From Regularization to Radial, Tensor and Additive Splines
(19930601)We had previously shown that regularization principles lead to approximation schemes, as Radial Basis Functions, which are equivalent to networks with one layer of hidden units, called Regularization Networks. In this ... 
Probabilistic Independence Networks for Hidden Markov Probability Models
(19960313)Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image ... 
Properties of Support Vector Machines
(19970801)Support Vector Machines (SVMs) perform pattern recognition between two point classes by finding a decision surface determined by certain points of the training set, termed Support Vectors (SV). This surface, which in some ... 
The Quadric Reference Surface: Theory and Applications
(19940601)The conceptual component of this work is about "reference surfaces'' which are the dual of reference frames often used for shape representation purposes. The theoretical component of this work involves the question ... 
Reciprocal Interactions Between Motion and Form Perception
(19950421)The processes underlying the perceptual analysis of visual form are believed to have minimal interaction with those subserving the perception of visual motion (Livingstone and Hubel, 1987; Victor and Conte, 1990). ... 
Recognizing Indoor Scenes
(20010725)We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides lowresolution spatial and spectral information. The ...