2D Object Detection and Recognition

By Yali Amit. 2002

126 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

In Media Technology

Citations in the corpus

Analysis of a Random Forests Model (2010, positive): “A good route to follow with this respect is given by the strategies outlined in Amit and Geman [3, Section 5.5].”
Object Detection (2020, background): “However, it may be difficult to specify models that capture the vast variability found in images.”
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? (2013, background): “…efficient matching can only be performed in several hierarchical stages, including Ettinger [42], Geman et al. [59], [60], Mel and Fiser [114], Amit [1], [2], Hawkins [69], Fidler et al. [45], Scalzo and Piater [152], Ullman and Epshtein [191], DiCarlo and Cox [31], Ommer and Buhmann [126], Serre…”
Fast Keypoint Recognition in Ten Lines of Code (2007, methodology): “The binary tests we use as classiﬁer features are picked completely at random, which puts our approach ﬁrmly in the camp of techniques that rely on randomization to achieve good performance [1].”
Visual Concepts and Compositional Voting (2017, methodology): “These models are similar to those in [1].”
Spatial priors for part-based recognition using statistical models (2005, background): “Since the 1970's it has been observed that many objects can be represented in terms of a set of parts arranged in a deformable configuration (e.g., [1] [2] [3] [6] [7] [8] [9] [10] [11]).”
Saliency and Gist Features for Target Detection in Satellite Images (2011, background): “The problem of target detection is a difﬁcult challenge in computer vision [1]–[3].”
Keypoint recognition using randomized trees (2006, background): “More specifically, we consider the set of all possible appearances of each individual object keypoint as a class, which we refer to as the view-set.”