SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.00163 · 2020

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

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

Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multiple Instance Learning (MIL) framework, where a bag (video) contains multiple instances (action segments). Since only the bag's label is known, the main challenge is assigning which key instances within the bag to trigger the bag's label. Most previous models use attention-based approaches applying attentions to generate the bag's representation from instances, and then train it via the bag's classification. These models, however, implicitly violate the MIL assumption that instances in negative bags should be uniformly negative. In this work, we explicitly model the key instances assignment as a hidden variable and adopt an Expectation-Maximization (EM) framework. We derive two pseudo-label generation schemes to model the E and M process and iteratively optimize the likelihood lower bound. We show that our EM-MIL approach more accurately models both the learning objective and the MIL assumptions. It achieves state-of-the-art performance on two standard benchmarks, THUMOS14 and ActivityNet1.2.

For agents

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

get_harvested_code_for_paper("2004.00163")
get_code_for_paper("2004.00163")
have("2004.00163")

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

curl https://syntology.ai/api/ran/2004.00163.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.00163.svg)](https://syntology.ai/paper/2004.00163)

Connect an agent — have() is free.