DSpace at MIT
(28,129 recursos)
This site is a university repository providing access to the publication output of the institution. Registered users can set up email alerts to notify them of newly added relevant content. A certain level of encryption and security is embedded in the site which may cause some users accessibility problems.
Mostrando recursos 101 - 120 de 123
101.
Global Depth Perception from Familiar Scene Structure - Torralba, Antonio; Oliva, Aude
In the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured.
102.
Bagging Regularizes - Poggio, Tomaso; Rifkin, Ryan; Mukherjee, Sayan; Rakhlin, Alex
Intuitively, we expect that averaging --- or bagging --- different regressors with low correlation should smooth their behavior and be somewhat similar to regularization.
103.
Stimulus Simplification and Object Representation: A Modeling Study - Knoblich, Ulf; Riesenhuber, Maximilan
(2001) recently studied the nature of object representation in monkey inferotemporal cortex using a combination of optical imaging and extracellular recordings.
104.
Categorization in IT and PFC: Model and Experiments - Knoblich, Ulf; Freedman, David J.; Riesenhuber, Maximilian
In this paper we analyze the tuning properties of view-tuned units in our HMAX model of object recognition in cortex (Riesenhuber 1999) using the same paradigm and stimuli as in the experiment.
105.
Modeling Stock Order Flows and Learning Market-Making from Data - Kim, Adlar J.; Shelton, Christian R.
Stock markets employ specialized traders, market-makers, designed to provide liquidity and volume to the market by constantly supplying both supply and demand.
109.
Perceptual Evaluation of Video-Realistic Speech - Geiger, Gadi; Ezzat, Tony; Poggio, Tomaso
We describe here our scheme and its application to a new video-realistic (potentially indistinguishable from real recorded video) visual-speech animation system, called Mary 101.
111.
Direction Estimation of Pedestrian from Images - Shimizu, Hiroaki; Poggio, Tomaso
The capability of estimating the walking direction of people would be useful in many applications such as those involving autonomous cars and robots.
112.
Investigating shape representation in area V4 with HMAX: Orientation and Grating selectivities - Kouh, Minjoon; Riesenhuber, Maximilian
While tuning properties of the cells in early part of the ventral visual stream, thought to be responsible for object recognition in the primate, are comparatively well understood, several different theories have been proposed regarding tuning in higher visual areas, such as V4.
115.
Risk Bounds for Mixture Density Estimation - Rakhlin, Alexander; Panchenko, Dmitry; Mukherjee, Sayan
In this paper we focus on the problem of estimating a bounded density using a finite combination of densities from a given class.
117.
Face processing in humans is compatible with a simple shape-based model of vision - Riesenhuber; Jarudi; Gilad; Sinha
Inspired by a large body of physiological evidence (Felleman and Van Essen, 1991; Hubel and Wiesel, 1962; Livingstone and Hubel, 1988; Tso et al., 2001; Zeki, 1993), a general class of recognition models has emerged which is based on a hierarchical organization of visual processing, with succeeding stages being sensitive to image features of increasing complexity (Hummel and Biederman, 1992; Riesenhuber and Poggio, 1999; Selfridge, 1959).
119.
Rotation Invariant Object Recognition from One Training Example - Yokono, Jerry Jun; Poggio, Tomaso
Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations.
120.
An Equivalence Between Sparse Approximation and Support Vector Machines - Girosi, Federico
In the first part of this paper we show a similarity between the principle of Structural Risk Minimization Principle (SRM) (Vapnik, 1982) and the idea of Sparse Approximation, as defined in (Chen, Donoho and Saunders, 1995) and Olshausen and Field (1996).
101.
