Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Abstract

In this paper, we tackle the problem of performing efficient co-localization in images and videos. Co-localization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images or videos. Building upon recent stateof-the-art methods, we show how we are able to naturally incorporate temporal terms and constraints for video co-localization into a quadratic programming framework. Furthermore, by leveraging the Frank-Wolfe algorithm (or conditional gradient), we show how our optimization formulations for both images and videos can be reduced to solving a succession of simple integer programs, leading to increased efficiency in both memory and speed. To validate our method, we present experimental results on the PASCAL VOC 2007 dataset for images and the YouTube-Objects dataset for videos, as well as a joint combination of the two.

DOI: 10.1007/978-3-319-10599-4_17

Extracted Key Phrases

0204020142015201620172018
Citations per Year

107 Citations

Semantic Scholar estimates that this publication has 107 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Joulin2014EfficientIA, title={Efficient Image and Video Co-localization with Frank-Wolfe Algorithm}, author={Armand Joulin and Kevin D. Tang and Fei-fei Li}, booktitle={ECCV}, year={2014} }