# Localizing Actions from Video Labels and Pseudo-Annotations

arXiv: https://arxiv.org/abs/1707.09143 · HTML: https://mlsanity.com/paper/1707.09143/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2017.

## Built on by (most cited first, 6 of 6)

- [End-to-End Semi-Supervised Learning for Video Action Detection](https://mlsanity.com/paper/2203.04251/) (2022)
- [Semi-supervised Active Learning for Video Action Detection](https://mlsanity.com/paper/2312.07169/) (2023)
- [Stable Mean Teacher for Semi-supervised Video Action Detection](https://mlsanity.com/paper/2412.07072/) (2024)
- [OmViD: Omni-supervised active learning for video action detection](https://mlsanity.com/paper/2508.13983/) (2025)
- [Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting](https://mlsanity.com/paper/2101.08567/) (2021)
- [Dual Guidance Semi-Supervised Action Detection](https://mlsanity.com/paper/2507.21247/) (2025)

## Abstract (arXiv)

The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive and effective algorithm that localizes actions from their class label only. We are inspired by recent work showing that unsupervised action proposals selected with human point-supervision perform as well as using expensive box annotations. Rather than asking users to provide point supervision, we propose fully automatic visual cues that replace manual point annotations. We call the cues pseudo-annotations, introduce five of them, and propose a correlation metric for automatically selecting and combining them. Thorough evaluation on challenging action localization datasets shows that we reach results comparable to results with full box supervision. We also show that pseudo-annotations can be leveraged during testing to improve weakly- and strongly-supervised localizers.