SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.03684 · ACL · 2020

Learning to Segment Actions from Observation and Narration

London, Stephen Clark, Jean-Baptiste Alayrac, Phil Blunsom, Chris Dyer, Daniel Fried, Aida Nematzadeh

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.03684")
get_code_for_paper("2005.03684")
have("2005.03684")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.03684.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.03684.svg)](https://syntology.ai/paper/2005.03684)

Connect an agent — have() is free.