SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.09234 · 2020

Learning to Abstract and Predict Human Actions

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

Human activities are naturally structured as hierarchies unrolled over time. For action prediction, temporal relations in event sequences are widely exploited by current methods while their semantic coherence across different levels of abstraction has not been well explored. In this work we model the hierarchical structure of human activities in videos and demonstrate the power of such structure in action prediction. We propose Hierarchical Encoder-Refresher-Anticipator, a multi-level neural machine that can learn the structure of human activities by observing a partial hierarchy of events and roll-out such structure into a future prediction in multiple levels of abstraction. We also introduce a new coarse-to-fine action annotation on the Breakfast Actions videos to create a comprehensive, consistent, and cleanly structured video hierarchical activity dataset. Through our experiments, we examine and rethink the settings and metrics of activity prediction tasks toward unbiased evaluation of prediction systems, and demonstrate the role of hierarchical modeling toward reliable and detailed long-term action forecasting.

For agents

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

get_harvested_code_for_paper("2008.09234")
get_code_for_paper("2008.09234")
have("2008.09234")

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

curl https://syntology.ai/api/ran/2008.09234.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.09234.svg)](https://syntology.ai/paper/2008.09234)

Connect an agent — have() is free.