SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.07593 · 2021

Weakly-Supervised Dense Action Anticipation

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

Dense anticipation aims to forecast future actions and their durations for long horizons. Existing approaches rely on fully-labelled data, i.e. sequences labelled with all future actions and their durations. We present a (semi-) weakly supervised method using only a small number of fully-labelled sequences and predominantly sequences in which only the (one) upcoming action is labelled. To this end, we propose a framework that generates pseudo-labels for future actions and their durations and adaptively refines them through a refinement module. Given only the upcoming action label as input, these pseudo-labels guide action/duration prediction for the future. We further design an attention mechanism to predict context-aware durations. Experiments on the Breakfast and 50Salads benchmarks verify our method's effectiveness; we are competitive even when compared to fully supervised state-of-the-art models. We will make our code available at: https://github.com/zhanghaotong1/WSLVideoDenseAnticipation.

For agents

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

get_harvested_code_for_paper("2111.07593")
get_code_for_paper("2111.07593")
have("2111.07593")

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

curl https://syntology.ai/api/ran/2111.07593.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.07593.svg)](https://syntology.ai/paper/2111.07593)

Connect an agent — have() is free.