# Action Recognition from Single Timestamp Supervision in Untrimmed Videos

## TL;DR

This paper introduces a weak supervision method for action recognition in untrimmed videos using single timestamps per action, reducing labeling effort while maintaining competitive accuracy.

## Contribution

The method replaces full temporal annotations with single timestamps and iteratively refines action segment localization, improving recognition performance with less supervision.

## Key findings

- Achieves comparable accuracy to fully supervised methods.
- Improves top-1 accuracy by up to 5.4%.
- Effective across multiple datasets with increasing action diversity.

## Abstract

Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision has been successfully exploited for recognition in untrimmed videos, however it is challenged when the number of different actions in training videos increases. We propose a method that is supervised by single timestamps located around each action instance, in untrimmed videos. We replace expensive action bounds with sampling distributions initialised from these timestamps. We then use the classifier's response to iteratively update the sampling distributions. We demonstrate that these distributions converge to the location and extent of discriminative action segments. We evaluate our method on three datasets for fine-grained recognition, with increasing number of different actions per video, and show that single timestamps offer a reasonable compromise between recognition performance and labelling effort, performing comparably to full temporal supervision. Our update method improves top-1 test accuracy by up to 5.4%. across the evaluated datasets.