Boosting Object Proposals:
From Pascal to COCO

In-depth analysis of the state-of-the-art in Object Proposals
and the challenges faced from Pascal to COCO

Publications

ICCV2015

Jordi Pont-Tuset and Luc Van Gool
Boosting Object Proposals: From Pascal to COCO
International Conference on Computer Vision (ICCV) 2015
[PDF] [BibTex]

@inproceedings{PTVG2015,
author = {Pont-Tuset, J. and Van Gool, L.},
title = {Boosting Object Proposals: From Pascal to COCO},
booktitle = {International Conference on Computer Vision},
year = {2015}
}
Please cite the paper if you found the resources of this web useful

Dataset Analysis

Analize the properties of the annotated objects in COCO compared to Pascal and SBD: Size, location, and category distribution statistics.

Benchmark State-of-the-Art

Display the evaluation of the current State-of-the-Art segmented object proposal tecniques in Pascal, SBD, and COCO; using a variety of measures and both at global and per-category level.
Is your technique missing although it's published and the code is public? Let us know and we'll add it.

Explore State-of-the-Art Results

Visualize the best segmented object proposal for all State-of-the-Art techniques on all 288.415 COCO objects, right from your browser.