Learning a Sparse Representation for Object Detection

By Shivani Agarwal, Dan Roth. 2002

673 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

Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation (2018, background): “This is not surprising; even the early computer vision datasets initially focused on single tasks such as faces [8] and cars [9].”
YOLACT: Real-Time Instance Segmentation (2019, neutral): “Others have designed prototypes for object detection [1, 45, 38].”
Large scale mining and retrieval of visual data in a multimodal context (2008, methodology): “even localize instances of object classes in images [Weber et al., 2000a; Agarwal and Roth, 2002]”
Fast Feature Pyramids for Object Detection (2014, background): “Alternative detection paradigms have been proposed [54], [55], [56], [57], [58], [59].”
Pedestrian Detection: An Evaluation of the State of the Art (2012, methodology): “Notable early approaches for unsupervised part learning, including the constellation model [79], [80] and the sparse representation approach of Agarwal and Roth [81], relied on keypoints.”
Efficient Classification for Additive Kernel SVMs (2013, methodology): “Example detections (green) and misdetections (red) of the detector on the UIUC cars dataset.”
Dataset Issues in Object Recognition (2006, background): “Current datasets, however, offer a somewhat limited range of image variability: Although the appearance (and to some extent, the shape) of objects does indeed vary within each class (e.g., among the airplanes, cars, faces, and motorbikes of Caltech 4), the viewpoints and orientations of different in”
An Affine Invariant Salient Region Detector (2004, background): “The selection of a set of image regions forms the first step in many computer vision algorithms, for example for computing image correspondences [2,17,19,20, 22], or for learning object categories [1,3,4,23].”
On-road vehicle detection: a review (2006, methodology): “Leung tested his algorithm on the UIUC data [78], showing slightly better performance.”
Cross-generalization: learning novel classes from a single example by feature replacement (2005, background): “Assume that for several object classes (e.g. horses and cows), a sufficient number of examples has been available to perform feature extraction by one of the existing methods [1] [17] [19].”
The Fastest Pedestrian Detector in the West (2010, background): “Numerous other detection frameworks have been proposed [2, 15, 20, 30], and although a full review is outside the scope of this work, the approximations we develop could potentially be applicable to such approaches as well.”
Weak Hypotheses and Boosting for Generic Object Detection and Recognition (2004, methodology): “Our approach performs better than the one of Agarwal and Roth but slightly worse than the approach of Fergus et al. Table 1 shows the results of our approach (using the affine invariant interest point detection and Moment Invariants) compared with the ones of Fergus et al. and other methods [23], [2”
Multiple Bernoulli relevance models for image and video annotation (2004, neutral): “Our model differs from traditional object recognition approaches in a number of ways (for example [9, 13, 1, 6, 4, 11].”
YOLACT++ Better Real-Time Instance Segmentation (2019, neutral): “Others have designed prototypes for object detection [44], [45], [46].”
Detection and Localization of Multiple Objects (2006, background): “However, most parts-based recognition algorithms still suffer from very high computational costs, even when a sparse object representation is used [9] [10].”