Non-maximum Suppression for Object Detection by Passing Messages Between Windows

By Rasmus Rothe, Matthieu Guillaumin, Luc Van Gool. 2014

211 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

Learning Non-maximum Suppression (2017, methodology): “Principled clustering formulations with globally optimal solutions have been proposed in [27, 23], although they have yet to surpass the performance of GreedyNMS.”
Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “For example, [26] first computes ov rlap betwee each pair of det ction boxe .”
Acquisition of Localization Confidence for Accurate Object Detection (2018, background): “[24] calculates an overlap matrix of all bounding boxes and performs affinity propagation clustering to select exemplars of clusters as the final detection results.”
Object detection by labeling superpixels (2015, background): “In [10, 41], context models are built to learn the context information to improve the heuristic nonmaximum suppression.”
Spatial Semantic Regularisation for Large Scale Object Detection (2015, methodology): “[22] successfully adapted APC to the task of selecting candidate object detections of the same class.”
Individualness and Determinantal Point Processes for Pedestrian Detection (2016, methodology): “However, APC is not naturally suitable for object detection since it does not explicitly penalize close exemplars which can be duplicated detections from the same object.”
Unconstrained Salient Object Detection via Proposal Subset Optimization (2016, methodology): “In [37], Affinity Propagation Clustering is used for bounding box filtering.”
Bounding Box Regression With Uncertainty for Accurate Object Detection (2018, methodology): “It is widely used in edge detection [44], feature point detection [37] and objection detection [13, 12, 42, 45].”
Object Detection in 20 Years: A Survey (2019, unknown): “Greedy selection is an old fashioned but the most popular way to perform NMS in object detection.”
A Convnet for Non-maximum Suppression (2015, background): “Recently Tang et al. (2015); Rothe et al. (2015) proposed principled clustering approaches that provide globally optimal solutions, however the results reached are on par, but do not surpass, GreedyNMS.”