Cracking BING and Beyond

By Qiyang Zhao, Zhibin Liu, Baolin Yin. 2014

39 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

What Makes for Effective Detection Proposals? (2015, methodology): “We survey these approaches in §2.1 and §2.2, followed by an overview of alternate approaches in §2.3 and baselines in §2.4.”
R-CNN minus R (2015, background): “Much faster proposal generators exist, but may not result in very accurate regions [22].”
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization (2016, methodology): “Implementation details: In the active box proposal algorithm we use 10 k seed boxes generated with a similar to Cracking Bing [43] technique 3 .”
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers (2015, background): “Cracking BING [27] showed that the BING classiﬁer has minimal impact on locating objects and without looking at the actual image a similar performance can be obtained.”
LocNet: Improving Localization Accuracy for Object Detection (2015, methodology): “[15] that includes a sliding window implementation inspired by BING [4, 38]). model ( Bbox reg.”
Improving object proposals with multi-thresholding straddling expansion (2015, background): “to capture the essential properties of generic objects [23].”
Towards Real-Time Object Detection on Embedded Systems (2018, background): “003 s, however, such a speed is obtained by excessive approximations [35], thus not adopted here.”
BING: Binarized normed gradients for objectness estimation at 300fps (2014, unknown): “[37] showed that this choice of window sizes along with the NMS is close to optimal.”