An Exemplar Model for Learning Object Classes

By Ondřej Chum, Andrew Zisserman. 2007

316 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

Ensemble of exemplar-SVMs for object detection and beyond (2011, background): “However, for object detection data-driven methods, such as [17, 14], have not been competitive against discriminative approaches (though the hybrid method of [6] comes close).”
Improving Generalization via Scalable Neighborhood Component Analysis (2018, background): “Exemplar-based models have shown to be effective for learning object classes [2] and object detection [25].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, neutral): “In Table 5, we quantitatively compare ours to previous results [8, 12, 47, 51] on PASCAL07-6x2.”
Large-Scale Weakly Supervised Object Localization via Latent Category Learning (2015, background): “In recent years, many studies have been proposed in weakly supervised localization, e.g., the exhaustive search [1], [2], [6], [24], multiple instance learning [3]–[5], [25], [26], interintra-class modeling [7]–[9], [27] and topic model [10], [11], [28]–[30].”
Is object localization for free? - Weakly-supervised learning with convolutional neural networks (2015, unknown): “Initial work [2, 8, 11, 20, 57] on weakly supervised object localization has focused on learning from images containing prominent and centered objects in scenes with limited background clutter.”
What Does Classifying More Than 10, 000 Image Categories Tell Us? (2010, methodology): “We choose SPM using BoW because it is a key component of many of the best recognition results [19,5,20,21] and is relatively efficient.”
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection (2018, background): “For example, Chum and Zisserman [33] ﬁrst initialize object locations by discriminative visual words and then introduce an exemplar model to measure similarity between image pairs for updating locations.”
Learning to Localize Objects with Structured Output Regression (2008, methodology): “Similar representations have been used successfully in many scenarios for object and scene classification [1,2,7,21,22].”
Weakly Supervised Object Localization with Latent Category Learning (2014, background): “, exhaustive search [5,20,21,36], multiple instance learning [13,28,34], inter-intra-class modeling [9, 23, 29, 35] and topic model [25, 30].”
Category Independent Object Proposals (2010, background): “, [7, 8]), which are found by searching naively over position and scale or by voting from learned codewords [9, 10], distinctive keypoints [11, 12], or regions [13].”
Multi-view object class detection with a 3D geometric model (2010, methodology): “A single spatial pyramid detector is used for the full object regions of interest (2D.3 top), while for each part region under each viewpoint, several smaller, overlapping spatial pyramid detectors are trained (2D.3 bottom).”
Pose estimation for category specific multiview object localization (2009, background): “Second, to achieve good localization performance, the classifier must be able to reject windows that only partially overlap with the object while at the same time being insensitive to object pose.”
Large Scale Visual Recognition (2012, methodology): “In the current state of the art, multiple descriptors and kernels are combined using either ad hoc or multiple kernel learning approaches [78, 71, 79, 80].”
Recognition by association via learning per-exemplar distances (2008, methodology): “[3] as well as the classification system of Frome et al.”