Learning to Segment Actions from Observation and Narration

Abstract

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity, our model performs competitively with previous work on a dataset of naturalistic instructional videos. Our model allows us to vary the sources of supervision used in training, and we find that both task structure and narrative language provide large benefits in segmentation quality.

arXiv commentACL 2020

References in corpus (5)

• The Kinetics Human Action Video Dataset
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Learning Video Representations using Contrastive Bidirectional Transformer
• Towards Automatic Learning of Procedures from Web Instructional Videos
• Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment

Cited by in corpus (1)

• A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos