Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem

被引：3

作者：

Cai, Hongping ^{[1
]}

Wu, Qi ^{[2
]}

Hall, Peter ^{[1
]}

机构：

[1] Univ Bath, Dept Comp Sci, Bath BA2 7AY, Avon, England

[2] Univ Adelaide, Sch Comp Sci, Adelaide, SA 5005, Australia

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW) | 2015年

关键词：

ADAPTATION;

D O I：

10.1109/ICCVW.2015.19

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It introduces great challenge as the variance across photo and art domains is much larger than either alone. We extensively evaluate classification, domain adaptation and detection benchmarks for leading techniques, demonstrating that none perform consistently well given the cross-depiction problem. Finally we refine the DPM model, based on query expansion, enabling it to bridge the gap across depiction boundaries to some extent.

引用

页码：74 / 79

页数：6