@inproceedings{13989a6a8734487dbd0cd041f340b189,
title = "Segmental spatiotemporal CNNs for fine-grained action segmentation",
abstract = "Joint segmentation and classification of fine-grained actions is important for applications of human-robot interaction, video surveillance, and human skill evaluation. However, despite substantial recent progress in large-scale action classification, the performance of stateof- the-art fine-grained action recognition approaches remains low. We propose a model for action segmentation which combines low-level spatiotemporal features with a high-level segmental classifier. Our spatiotemporal CNN is comprised of a spatial component that represents relationships between objects and a temporal component that uses large 1D convolutional filters to capture how object relationships change across time. These features are used in tandem with a semi-Markov model that captures transitions from one action to another. We introduce an efficient constrained segmental inference algorithm for this model that is orders of magnitude faster than the current approach. We highlight the effectiveness of our Segmental Spatiotemporal CNN on cooking and surgical action datasets for which we observe substantially improved performance relative to recent baseline methods.",
author = "Colin Lea and Austin Reiter and Ren{\'e} Vidal and Hager, {Gregory D.}",
note = "Funding Information: This work was funded in part by grants NIH R01HD87133-01, ONR N000141310116, and an Intuitive Surgical Research Grant. 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 = "10.1007/978-3-319-46487-9_3",
language = "English (US)",
isbn = "9783319464862",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "36--52",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
}