@inproceedings{cbe7c3653e844629a3ba0cd8ef329f7e,
title = "Cats: Co-saliency activated tracklet selection for video co-localization",
abstract = "Video co-localization is the task of jointly localizing common objects across videos. Due to the appearance variations both across the videos and within the video, it is a challenging problem to identify and track them without any supervision. In contrast to previous joint frameworks that use bounding box proposals to attack the problem, we propose to leverage co-saliency activated tracklets to address the challenge. To identify the common visual object, we first explore inter-video commonness, intra-video commonness, and motion saliency to generate the co-saliency maps. Object proposals of high objectness and co-saliency scores are tracked across short video intervals to build tracklets. The best tube for a video is obtained through tracklet selection from these intervals based on confidence and smoothness between the adjacent tracklets, with the help of dynamic programming. Experimental results on the benchmark YouTube Object dataset show that the proposed method outperforms state-of-the-art methods.",
keywords = "Cats, Co-detection, Co-localization, Co-saliency, Tracklet, Video",
author = "Jerripothula, \{Koteswar Rao\} and Jianfei Cai and Junsong Yuan",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 14th European Conference on Computer Vision, ECCV 2016 ; Conference date: 08-10-2016 Through 16-10-2016",
year = "2016",
doi = "10.1007/978-3-319-46478-7\_12",
language = "English",
isbn = "9783319464770",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "187--202",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
address = "Germany",
}