• Publications
  • Influence
Non-parametric Model for Background Subtraction
We present a novel non-parametric background model and a background subtraction approach that enables very sensitive detection of moving targets. Expand
  • 2,166
  • 182
  • Open Access
Background and foreground modeling using nonparametric kernel density estimation for visual surveillance
Automatic understanding of events happening at a site is the ultimate goal for many visual surveillance systems. Higher level understanding of events requires that certain lower level computer visionExpand
  • 994
  • 59
  • Open Access
Inferring 3D body pose from silhouettes using activity manifold learning
We aim to infer 3D body pose directly from human silhouettes. Expand
  • 349
  • 32
SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition
We propose a new CNN architecture that integrates semantic part detection and abstraction (SPDACNN) for fine-grained classification. Expand
  • 166
  • 27
  • Open Access
Nonparametric background model for background subtraction
  • 224
  • 18
Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
We develop a machine that is able to make aesthetic-related semantic-level judgments, such as predicting a painting's style, genre, and artist, as well as providing similarity measures optimized based on the knowledge available in the domain of art historical interpretation. Expand
  • 89
  • 16
  • Open Access
Probabilistic framework for segmenting people under occlusion
  • A. Elgammal, L. Davis
  • Computer Science
  • Proceedings Eighth IEEE International Conference…
  • 7 July 2001
We address the problem of segmenting foreground regions corresponding to a group of people given models of their appearance that were initialized before occlusion. Expand
  • 205
  • 15
  • Open Access
Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
We propose an approach for zero-shot learning of object categories where the description of unseen categories comes in the form of typical text such as an encyclopedia entry, without the need to explicitly defined attributes. Expand
  • 212
  • 14
  • Open Access
Online Moving Camera Background Subtraction
We present a method which enables learning of pixel based models for foreground and background regions and, in addition, segments each frame in an online framework. Expand
  • 103
  • 13
  • Open Access
Learning dynamics for exemplar-based gesture recognition
We propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution. Expand
  • 122
  • 12
  • Open Access