Self-supervised Multi-task Procedure Learning from Instructional Videos
- 19 November 2020
- book chapter
- Published by Springer Nature
- p. 557-573
Abstract
No abstract availableKeywords
This publication has 24 references indexed in Scilit:
- Deep Clustering for Unsupervised Learning of Visual Features2018
- Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling2017
- Connectionist Temporal Modeling for Weakly Supervised Action Labeling2016
- Unsupervised Learning from Narrated Instruction Videos2016
- Unsupervised Semantic Parsing of Video Collections2015
- Fully convolutional networks for semantic segmentation2015
- What’s Cookin’? Interpreting Cooking Videos using Text, Speech and Vision2015
- Instructional Videos for Unsupervised Harvesting and Learning of Action Examples2014
- Weakly Supervised Action Labeling in Videos under Ordering Constraints2014
- Web-scale k-means clustering2010