Proceedings Article10.1109/CVPR.2004.479
Workshop on Generic Object Recognition and Categorization
Sven Dickinson,Ales Leonardis,Bernt Schiele +2 more
- 27 Jun 2004
- pp 26-26
TL;DR: It is argued that high-level, volumetric part-based descriptions are essential in the process of recognizing objects that might never have been observed before, and for which no exact geometric model is available.
read more
Abstract: We discuss the issues and challenges of generic object recognition. We argue that high-level, volumetric part-based descriptions are essential in the process of recognizing objects that might never have been observed before, and for which no exact geometric model is available. We discuss the representation scheme and its relationships to the three main tasks to solve: extracting descriptions from real images, under a wide variety of viewing conditions; learning new objects by storing their description in a database; recognizing objects by matching their description to that of similar previously observed objects.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Trainable Visual Models for Object Class Recognition.
Andrew Zisserman
- 01 Jan 2004
TL;DR: A number of successes have been achieved by using ideas and algorithms from statistical learning theory, where visual models are trained using positive and negative examples of the class.
References
A sparse texture representation using local affine regions
TL;DR: The proposed texture representation is evaluated in retrieval and classification tasks using the entire Brodatz database and a publicly available collection of 1,000 photographs of textured surfaces taken from different viewpoints.
Categorical Representation of Visual Stimuli in the Primate Prefrontal Cortex
David J. Freedman,Maximilian Riesenhuber,Maximilian Riesenhuber,Tomaso Poggio,Tomaso Poggio,Earl K. Miller +5 more
TL;DR: This article trained monkeys to categorize computer-generated stimuli as "cat" and "dogs" using a morphing system to systematically vary stimulus shape and precisely define the category boundary, which reflected the category of visual stimuli even when a monkey was retrained with the stimuli assigned to new categories.
•Proceedings Article
Object Recognition with Informative Features and Linear Classification
Michel Vidal-Naquet,Shimon Ullman +1 more
- 13 Oct 2003
TL;DR: The results show that by maximizing the individual information of the features, it is possible to obtain efficient classification by a simple linear separating rule, as well as more efficient learning.
297
Object recognition with informative features and linear classification
Vidal-Naquet,Ullman +1 more
- 01 Jan 2003
TL;DR: In this paper, the authors demonstrate the superiority of informative class-specific features, as compared with generic type features such as wavelets, for the task of object recognition, and show that information rich features can reach optimal performance with simple linear separation rules, while generic feature based classifiers require more complex classification schemes.
3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints
Fred Rothganger,Svetlana Lazebnik,Cordelia Schmid,Jean Ponce +3 more
- 18 Jun 2003
TL;DR: Multi-view constraints associated with groups of patches are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true three-dimensional affine and Euclidean models from multiple images and their recognition in a single photograph taken from an arbitrary viewpoint.