# Detecting the Moment of Completion: Temporal Models for Localising Action Completion

arXiv: https://arxiv.org/abs/1710.02310 · HTML: https://mlsanity.com/paper/1710.02310/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2017.

## Built on by (most cited first, 3 of 3)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Learning Object State Changes in Videos: An Open-World Perspective](https://mlsanity.com/paper/2312.11782/) (2023)
- [Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts](https://mlsanity.com/paper/2104.06779/) (2021)

## Abstract (arXiv)

Action completion detection is the problem of modelling the action's progression towards localising the moment of completion - when the action's goal is confidently considered achieved. In this work, we assess the ability of two temporal models, namely Hidden Markov Models (HMM) and Long-Short Term Memory (LSTM), to localise completion for six object interactions: switch, plug, open, pull, pick and drink. We use a supervised approach, where annotations of pre-completion and post-completion frames are available per action, and fine-tuned CNN features are used to train temporal models. Tested on the Action-Completion-2016 dataset, we detect completion within 10 frames of annotations for ~75% of completed action sequences using both temporal models. Results show that fine-tuned CNN features outperform hand-crafted features for localisation, and that observing incomplete instances is necessary when incomplete sequences are also present in the test set.