Proposal generation for object detection using cascaded ranking SVMs

By Ziming Zhang, Jonathan H. Warrell, Philip H. S. Torr. 2011

115 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

What Makes for Effective Detection Proposals? (2015, background): “Methods that operate on videos and require temporal information (e.g. [33]) are considered outside the scope of this work.”
Cracking BING and Beyond (2014, background): “In most time, its DR's are higher than OBN and CSVM, and close to SEL and BING.”
Learning a category independent object detection cascade (2011, methodology): “The discriminative training of [26] is perhaps the most closely related approach to our method, and uses a very similar objective for cascade optimization.”
Regionlets for Generic Object Detection (2013, methodology): “The exhaust ive search can be accelerated by more efficient search methods as in [5], [28], [4], [6], [26], [23], [29].”
Salient object detection: A survey (2014, background): “ve been studied in different background and problem focuses: including salient object detection [8], [86], [115], [139], ﬁxation prediction [1], [18], [60], and object proposal generation [57], [64]– [67]. Salient object detection models usually aim to detect only the most salient objects in a scene”
Generating Object Segmentation Proposals Using Global and Local Search (2014, methodology): “Still, if a full ordering of the proposal regions would be necessary, our regions could be ranked using the techniques presented in [5] or [4], and also [14] or [18] if bounding boxes are used instead of the original regions.”
Oriented Object Proposals (2015, methodology): “Zhang et al. [31] and Rahtu et al. [24] extend this idea to use cascaded ranking SVM and structured output ranking, respectively, to combine different cues.”
Non Maximal Suppression in Cascaded Ranking Models (2013, methodology): “Many recent systems perform greedy optimization based on overlap or a probabilistic detection measure [15, 16, 1, 2].”
Pattern Recognition (2015, unknown): “Important aspects of this problem include 3D layout estimation [15,36], object detection [35,39], as well as semantic segmentation [14,32].”