Multiclass Object Recognition with Sparse, Localized Features

By Jim Mutch, David G. Lowe. 2006

548 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, neutral): “[20], pedestrian detection [21], activity detection [22], [23], [24], [25], etc.”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
Brain-Inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform (2014, methodology): “Both convolutional neural networks and HMAX have been used to solve a variety of real-world computer vision tasks such as image classification [17][19][21] and scene labeling [9][10].”
Learning Visual Representations using Images with Captions (2007, background): “When few labeled examples are available, most current supervised learning methods [22, 10, 12, 18, 14] for image classification may work poorly.”
Human Activity Detection from RGBD Images (2011, methodology): “Hierarchical techniques for activity recognition have been used as well, but these typically focus on neurologically-inspired visual cortex-type models (Giese and Poggio, 2003; Serre, Wolf, and Poggio, 2005; Mutch and Lowe, 2006; Ran-zato et al., 2007).”
CNP: An FPGA-based processor for Convolutional Networks (2009, methodology): “The design is specifically geared towards Convolutional Networks [1, 2], but can be used for many similar architectures based on local filter banks and classifiers, such as HMAX [3, 4], and HoG methods [5].”
Why is Real-World Visual Object Recognition Hard? (2008, unknown): “Some of the other models whose performance is shown in Figure 1 were biologically inspired, and thus also have V1-like stages contained within them, as wellas additionalmachinery intended toallow invariant object recognition (e.g., [2,19]).”
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition (2007, methodology): “Serre et al. [20] achieved an average accuracy of 42%, while Mutch and Lowe [17] improved it to 56%.”
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition (2008, methodology): “When multiple such levels are stacked, the resulting architecture is essentially identical to the Neocognitron [7], the Convolutional Network [13] [10], and the HMAX, or so-called " Standard Model " architecture [20] [17].”
Class-specific Hough forests for object detection (2009, background): “The UIUC car dataset [1] contains images of side views of cars.”
A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction (2015, background): “, max-pooling [13], [14], [17], [18], average-pooling [12], [13], or sub-sampling [16]).”
Group-sensitive multiple kernel learning for object categorization (2009, unknown): “We compare our GS-MKL approach with several recent methods [2-4, 6, 11, 14, 18, 26, 27].”
FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review (2019, background): “image classification [27]–[32], face detection and recognition [33], [34], robot navigation [35]–[37], real-time multiple object tracking [38], financial forecasting [39], and medical diagnosis systems [40]–[42], to name a few.”
Object detection using a max-margin Hough transform (2009, unknown): “5 % Mutch & Lowe [21] 99.”
Beyond sliding windows: Object localization by efficient subwindow search (2008, unknown): “methodndata set single scale multi scale ESS w/ 10 10 pyramid 1.5 % 1:4% ESS w/ 4 4 pyramid 1.5 % 7:9% ESS w/ bag-of-visual-words 10.0 % 71:2% Agarwal et al. [1] 23:5% 60:4% Fergus et al. [10] 11:5% — Leibe et al. [15] 2:5% 5:0% Fritz et al. [12] 11:4% 12:2% Mutch/Lowe [ 18 ] 0:04% 9:4%”