# STEP: Spatio-Temporal Progressive Learning for Video Action Detection

arXiv: https://arxiv.org/abs/1904.09288 · HTML: https://mlsanity.com/paper/1904.09288/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2019.

## Built on by (most cited first, 30 of 51)

- [Towards Long-Form Video Understanding](https://mlsanity.com/paper/2106.11310/) (2021)
- [MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions](https://mlsanity.com/paper/2105.07404/) (2021)
- [TubeR: Tubelet Transformer for Video Action Detection](https://mlsanity.com/paper/2104.00969/) (2021)
- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [Unified Graph Structured Models for Video Understanding](https://mlsanity.com/paper/2103.15662/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Context Understanding in Computer Vision: A Survey](https://mlsanity.com/paper/2302.05011/) (2023)
- [STMixer: A One-Stage Sparse Action Detector](https://mlsanity.com/paper/2303.15879/) (2023)
- [Dual DETRs for Multi-Label Temporal Action Detection](https://mlsanity.com/paper/2404.00653/) (2024)
- [ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2112.10977/) (2021)
- [End-to-End Semi-Supervised Learning for Video Action Detection](https://mlsanity.com/paper/2203.04251/) (2022)
- [Spatio-Temporal Action Detection Under Large Motion](https://mlsanity.com/paper/2209.02250/) (2022)
- [Video Action Detection: Analysing Limitations and Challenges](https://mlsanity.com/paper/2204.07892/) (2022)
- [Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization](https://mlsanity.com/paper/2303.11003/) (2023)
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://mlsanity.com/paper/2202.00182/) (2022)
- [Semi-supervised Active Learning for Video Action Detection](https://mlsanity.com/paper/2312.07169/) (2023)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization](https://mlsanity.com/paper/2502.07707/) (2025)
- [ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation](https://mlsanity.com/paper/2102.13493/) (2021)
- [MINOTAUR: Multi-task Video Grounding From Multimodal Queries](https://mlsanity.com/paper/2302.08063/) (2023)
- [CathAction: A Benchmark for Endovascular Intervention Understanding](https://mlsanity.com/paper/2408.13126/) (2024)
- [On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes](https://mlsanity.com/paper/2410.19553/) (2024)
- [MRSN: Multi-Relation Support Network for Video Action Detection](https://mlsanity.com/paper/2304.11975/) (2023)
- [A Survey on Deep Learning-based Spatio-temporal Action Detection](https://mlsanity.com/paper/2308.01618/) (2023)
- [Open-Vocabulary Spatio-Temporal Action Detection](https://mlsanity.com/paper/2405.10832/) (2024)
- [Hierarchical Deep Residual Reasoning for Temporal Moment Localization](https://mlsanity.com/paper/2111.00417/) (2021)
- [The Use of Video Captioning for Fostering Physical Activity](https://mlsanity.com/paper/2104.03207/) (2021)
- [CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection](https://mlsanity.com/paper/2303.16118/) (2023)
- [Spatio-Temporal Context Prompting for Zero-Shot Action Detection](https://mlsanity.com/paper/2408.15996/) (2024)

## Abstract (arXiv)

In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach progressively refines the proposals towards actions over a few steps. In this way, high-quality proposals (i.e., adhere to action movements) can be gradually obtained at later steps by leveraging the regression outputs from previous steps. At each step, we adaptively extend the proposals in time to incorporate more related temporal context. Compared to the prior work that performs action detection in one run, our progressive learning framework is able to naturally handle the spatial displacement within action tubes and therefore provides a more effective way for spatio-temporal modeling. We extensively evaluate our approach on UCF101 and AVA, and demonstrate superior detection results. Remarkably, we achieve mAP of 75.0% and 18.6% on the two datasets with 3 progressive steps and using respectively only 11 and 34 initial proposals.