An Algorithm for Data-Driven Bandwidth Selection

By Dorin Comaniciu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003

403 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/365129731fdfa1a9948d56f0caecb8642cc98c32

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

In Molecular Biology

Citations in the corpus

Human Detection Using Oriented Histograms of Flow and Appearance (2006, background): “Negative scores are zeroed and a 3D position-scale mean shift process [2] is run to identify significant local peaks in the resulting score.”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, background): “Assuming that classifiers provide a peak at the correct position and scale of the target and weaker responses around it, Dalal [110] makes use of mean shift [111] to find the minimum set of ROIs that best adjust to the pedestrians in the image.”
Modelling beyond regression functions: an application of multimodal regression to speed–flow data (2006, methodology): “Comaniciu & Meer (2002) show that (13) corresponds (in the unconditional case) to location M estimation.”
Finding People in Images and Videos (2006, methodology): “Basically, negative scores from the linear SVM are zeroed and a 3D position-scale mean shift process [Comaniciu 2003b] is run to identify significant local peaks in the resulting score.”
A Review on Modal Clustering (2016, methodology): “In the context of mean-shift clustering, Comaniciu (2003) presents a bandwidth selection method producing a stable estimate of the second-order moments of the data distribution across different scales.”
Simplifying Mixture Models Through Function Approximation (2006, background): “As is briefly reviewed in Section III-B, the mean shift algorithm is a density-based, nonparametric modeseeking algorithm that has been widely used in various computer vision problems such as tracking, segmentation, and video processing.”
Multi-cue onboard pedestrian detection (2009, methodology): “Here, we adopt an adapted bandwidth mean-shift based mode seeking strategy [3] to determine the position in x - y - scale -space, but determine the ﬁnal detection’s score to be the maximum of all scores within the mode.”
Color Image Segmentation Based on Mean Shift and Normalized Cuts (2007, methodology): “In this section, we present a brief review of the image segmentation method based on the MS procedure [4], [9], [10].”
Sliding-Windows for Rapid Object Class Localization: A Parallel Technique (2008, methodology): “To obtain a single nal hypothesis for each object, these detections are fused with a non-maximum suppression algorithm, a scale adaptive bandwidth mean shift [19].”