# Precise Temporal Action Localization by Evolving Temporal Proposals

arXiv: https://arxiv.org/abs/1804.04803 · HTML: https://mlsanity.com/paper/1804.04803/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2018.

## Built on by (most cited first, 4 of 4)

- [Class Semantics-based Attention for Action Detection](https://mlsanity.com/paper/2109.02613/) (2021)
- [Self-Feedback DETR for Temporal Action Detection](https://mlsanity.com/paper/2308.10570/) (2023)
- [Temporal Action Localization Using Gated Recurrent Units](https://mlsanity.com/paper/2108.03375/) (2021)
- [Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning](https://mlsanity.com/paper/2606.09289/) (2026)

## Abstract (arXiv)

Locating actions in long untrimmed videos has been a challenging problem in video content analysis. The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action. Imitating the human perception procedure with observations and refinements, we propose a novel three-phase action localization framework. Our framework is embedded with an Actionness Network to generate initial proposals through frame-wise similarity grouping, and then a Refinement Network to conduct boundary adjustment on these proposals. Finally, the refined proposals are sent to a Localization Network for further fine-grained location regression. The whole process can be deemed as multi-stage refinement using a novel non-local pyramid feature under various temporal granularities. We evaluate our framework on THUMOS14 benchmark and obtain a significant improvement over the state-of-the-arts approaches. Specifically, the performance gain is remarkable under precise localization with high IoU thresholds. Our proposed framework achieves mAP@IoU=0.5 of 34.2%.