Paper in ECCV Workshop 2012: “Weakly Supervised Learning of Object Segmentations from Web-Scale Videos”

@inproceedings{2012-Hartmann-WSLOSFWV,

title = {Weakly Supervised Learning of Object Segmentations from Web-Scale Videos},

author = {Glenn Hartmann and Matthias Grundmann and Judy Hoffman and David Tsai and Vivek Kwatra and Omid Madani and Sudheendra Vijayanarasimhan and Irfan Essa and James Rehg and Rahul Sukthankar},

url = {https://link.springer.com/chapter/10.1007/978-3-642-33863-2_20

https://research.google.com/pubs/archive/40735.pdf

},

doi = {10.1007/978-3-642-33863-2_20},

year  = {2012},

date = {2012-10-01},

urldate = {2012-10-01},

booktitle = {Proceedings of ECCV 2012 Workshop on Web-scale Vision and Social Media},

abstract = {We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specifically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as “dog”, without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classifiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classifiers are further refined using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we confirm that our proposed methods can learn good object masks just by watching YouTube.



},

keywords = {awards, best paper award, computer vision, ECCV, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}