标题:Generic Promotion of Diffusion-Based Salient Object Detection
作者:Jiang, Peng; Vasconcelos, Nuno; Peng, Jingliang
通讯作者:Peng, Jingliang
作者机构:[Jiang, Peng; Peng, Jingliang] Shandong Univ, Jinan, Shandong, Peoples R China.; [Vasconcelos, Nuno] Univ Calif San Diego, San Diego, CA 92103 USA.
会议名称:IEEE International Conference on Computer Vision
会议日期:DEC 11-18, 2015
来源:2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
出版年:2015
卷:2015 International Conference on Computer Vision, ICCV 2015
页码:217-225
DOI:10.1109/ICCV.2015.33
摘要:In this work, we propose a generic scheme to promote any diffusion-based salient object detection algorithm by original ways to re-synthesize the diffusion matrix and construct the seed vector. We first make a novel analysis of the working mechanism of the diffusion matrix, which reveals the close relationship between saliency diffusion and spectral clustering. Following this analysis, we propose to re-synthesize the diffusion matrix from the most discriminative eigenvectors after adaptive re-weighting. Further, we propose to generate the seed vector based on the readily available diffusion maps, avoiding extra computation for color-based seed search.; As a particular instance, we use inverse normalized Laplacian matrix as the original diffusion matrix and promote the corresponding salient object detection algorithm, which leads to superior performance as experimentally demonstrated.
收录类别:CPCI-S;EI;SCOPUS
WOS核心被引频次:22
Scopus被引频次:29
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84973922977&doi=10.1109%2fICCV.2015.33&partnerID=40&md5=354bd03f96198191fbadf7d7b71ab7e6
TOP