Optimal scanning for faster object detection

By Nicholas J. Butko, Javier R. Movellan. 2009

115 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, methodology): “, 2005), or via Policy Gradients (Butko and Movellan, 2009).”
Crosstalk Cascades for Frame-Rate Pedestrian Detection (2012, methodology): “[14,15,16] propose to first compute a sparse set of detector responses and then sample more densely around promising locations; we use similar intuition for excitation of promising neighbors, but do so during every stage of detection for greater gains.”
Salient object detection by composition (2011, methodology): “Extensive evaluation on challenging object detection datasets verifies better efficacy and efficiency of the proposed method comparing to the state-of-the-art, making it a good pre-processing tool for subsequent applications.”
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video (2016, methodology): “These existing methods categorize an image (recognition), search for an object (detection) [10]–[12], [15] or perform structured prediction [41].”
Recurrent Models of Visual Attention (2014, methodology): “[4] employs the learned Bayesian observer model from [5] to the task of object detection.”
Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks (2017, background): “Recent work considers tasks such as active object localization [4, 10, 17, 21, 32,45,46,56,77], action detection in video [73], and object recognition [3,29,31,43] including foveated vision systems that selectively obtain higher resolution data [9, 20, 53].”
State-of-the-Art in Visual Attention Modeling (2013, unknown): “Butko and Movellan [161] modeled object search based on the same principles of visual search as stated by Najemnik and Geisler [20] in a partially observable framework for face detection and tracking, but they did not apply it to explain eye fixations while searching for a face.”