# Action Recognition from Single Timestamp Supervision in Untrimmed Videos

arXiv: https://arxiv.org/abs/1904.04689 · HTML: https://mlsanity.com/paper/1904.04689/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 31)

- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Temporal Action Segmentation from Timestamp Supervision](https://mlsanity.com/paper/2103.06669/) (2021)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Background-Click Supervision for Temporal Action Localization](https://mlsanity.com/paper/2111.12449/) (2021)
- [Timestamp-Supervised Action Segmentation with Graph Convolutional Networks](https://mlsanity.com/paper/2206.15031/) (2022)
- [FIFA: Fast Inference Approximation for Action Segmentation](https://mlsanity.com/paper/2108.03894/) (2021)
- [Constraint and Union for Partially-Supervised Temporal Sentence Grounding](https://mlsanity.com/paper/2302.09850/) (2023)
- [Less is More: Surgical Phase Recognition from Timestamp Supervision](https://mlsanity.com/paper/2202.08199/) (2022)
- [DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2307.16415/) (2023)
- [OnlineTAS: An Online Baseline for Temporal Action Segmentation](https://mlsanity.com/paper/2411.01122/) (2024)
- [Robust Action Segmentation from Timestamp Supervision](https://mlsanity.com/paper/2210.06501/) (2022)
- [Action-Agnostic Point-Level Supervision for Temporal Action Detection](https://mlsanity.com/paper/2412.21205/) (2024)
- [Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency](https://mlsanity.com/paper/2305.02734/) (2023)
- [Contrast-Unity for Partially-Supervised Temporal Sentence Grounding](https://mlsanity.com/paper/2502.12917/) (2025)
- [Weakly-Supervised Dense Action Anticipation](https://mlsanity.com/paper/2111.07593/) (2021)
- [Faster Video Moment Retrieval with Point-Level Supervision](https://mlsanity.com/paper/2305.14017/) (2023)
- [Learning Temporal Sentence Grounding From Narrated EgoVideos](https://mlsanity.com/paper/2310.17395/) (2023)
- [Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization](https://mlsanity.com/paper/2205.00400/) (2022)
- [Proposal-based Temporal Action Localization with Point-level Supervision](https://mlsanity.com/paper/2310.05511/) (2023)
- [Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting](https://mlsanity.com/paper/2403.14240/) (2024)
- [A Generalized & Robust Framework For Timestamp Supervision in Temporal Action Segmentation](https://mlsanity.com/paper/2207.10137/) (2022)
- [Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2309.09060/) (2023)
- [POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization](https://mlsanity.com/paper/2310.13585/) (2023)
- [Weakly-Supervised Action Detection Guided by Audio Narration](https://mlsanity.com/paper/2205.05895/) (2022)
- [Distill and Collect for Semi-Supervised Temporal Action Segmentation](https://mlsanity.com/paper/2211.01311/) (2022)
- [Dilation-Erosion for Single-Frame Supervised Temporal Action Localization](https://mlsanity.com/paper/2212.06348/) (2022)
- [ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization](https://mlsanity.com/paper/2311.15916/) (2023)
- [SFGANS Self-supervised Future Generator for human ActioN Segmentation](https://mlsanity.com/paper/2401.00438/) (2023)
- [Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment](https://mlsanity.com/paper/2602.01257/) (2026)

## Abstract (arXiv)

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.