Object Ranking on Deformable Part Models with Bagged LambdaMART

Autor:	Peng Lu, Chaobo Sun, Xiaojie Wang
Rok vydání:	2015
Předmět:	Computer science Local binary patterns business.industry Pattern recognition Object (computer science) Machine learning computer.software_genre Convolutional neural network Object detection Binary classification Ranking Classification methods Artificial intelligence Detection rate business computer
Zdroj:	Computer Vision--ACCV 2014 ISBN: 9783319168074 ACCV (2)
DOI:	10.1007/978-3-319-16808-1_5
Popis:	Object detection methods based on sliding windows has long been considered a binary classification problem, but this formulation ignores order of examples. Deformable part models, which achieves great success in object detection, have the same problem.This paper aims to give better order to detections given by deformable part models. We use a bagged LambdaMART to model both pair-wise and list-wise relationships between detections. Experiments show our ranking models not only significantly improve detection rates compared to basic deformable part model detectors, but also outperform classification methods with same features.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::bb70537b60165ff2512856142910e574 https://doi.org/10.1007/978-3-319-16808-1_5 Zobrazit plný text záznamu