Microsoft COCO: Common Objects in Context

被引：30766

作者：

Lin, Tsung-Yi ^{[1
]}

Maire, Michael ^{[2
]}

Belongie, Serge ^{[1
]}

Hays, James ^{[3
]}

Perona, Pietro ^{[2
]}

Ramanan, Deva ^{[4
]}

Dollar, Piotr ^{[5
]}

Zitnick, C. Lawrence ^{[5
]}

机构：

[1] Cornell, Ithaca, NY 14850 USA

[2] CALTECH, Pasadena, CA 91125 USA

[3] Brown Univ, Providence, RI 02912 USA

[4] Univ Calif Irvine, Irvine, CA 92717 USA

[5] Microsoft Res, New York, NY USA

来源：

COMPUTER VISION - ECCV 2014, PT V | 2014年 / 8693卷

关键词：

D O I：

10.1007/978-3-319-10602-1_48

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

引用

页码：740 / 755

页数：16

共 51 条

[41] ImageNet Classification with Deep Convolutional Neural Networks [J].