A statistical approach to 3d object detection applied to faces and cars
By Henry Schneiderman, Takeo Kanade, Carnegie Mellon, Alex Pentland, Dean A. Pomerleau, Assistware Technology, A. Lipton, Rahul Sukthankar, Tim W. Doebler, Larry E. Ray and 27 more. 2000
294 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/3737d479a5764eecef0cee5081e64f5f884508b1
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Li Fei-Fei
- Yoshua Bengio
- Trevor Darrell
- Sergey Levine
- Kristen Grauman
- Andrew Zisserman
- Abhinav Kumar Gupta
- Jitendra Malik
Citations in the corpus
- The Shape Boltzmann Machine: A Strong Model of Object Shape (2012, background): “An alternative way to achieve large-scale translation invariance is through a model that is defined only for a tight bounding box enclosing the shape and which is then explicitly translated to all possible image positions (e.g. Frey et al, 2003; Williams and Titsias, 2004; similar to the sliding win”
- Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery (2010, background): “While most of the work has focussed on representing objects as 2D models [4,13,8] or collections of 2D models [23], very few methods have tried to combine in a principled way the appearance information that is captured by images and the intrinsic 3D structure representative of an object category.”
- 3D generic object categorization, localization and pose estimation (2007, unknown): “The algorithm therefore learns a different model (or a mixture of models) for each of these classes [21, 26, 24].”
- A multi-view probabilistic model for 3D object classes (2009, unknown): “*indicates equal contributions els [27, 33].”
- A Bayesian approach to unsupervised one-shot learning of object categories (2003, methodology): “These have to be collected, and sometimes manually segmented and aligned [2, 3, 4, 5, 6, 7] – a tedious and expensive task.”
- Learning object detection from a small number of examples: the importance of good features (2004, methodology): “While global orientation histograms have been used extensively in a wide range of vision applications (e.g. [2, 10, 9]) the use of localized orientation histograms for object detection, is to the best of our knowledge, novel.”