@inproceedings{6f563484693747d28e4079be4b73d0ce,
title = "Best of both worlds: Human-machine collaboration for object annotation",
abstract = "The long-standing goal of localizing every object in an image remains elusive. Manually annotating objects is quite expensive despite crowd engineering innovations. Current state-of-the-art automatic object detectors can accurately detect at most a few objects per image. This paper brings together the latest advancements in object detection and in crowd engineering into a principled framework for accurately and efficiently localizing objects in images. The input to the system is an image to annotate and a set of annotation constraints: desired precision, utility and/or human cost of the labeling. The output is a set of object annotations, informed by human feedback and computer vision. Our model seamlessly integrates multiple computer vision models with multiple sources of human input in a Markov Decision Process. We empirically validate the effectiveness of our human-in-the-loop labeling approach on the ILSVRC2014 object detection dataset.",
author = "Olga Russakovsky and Li, {Li Jia} and Li Fei-Fei",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",
year = "2015",
month = oct,
day = "14",
doi = "10.1109/CVPR.2015.7298824",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "2121--2131",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",
address = "United States",
}