# Decoupling Localization and Classification in Single Shot Temporal Action Detection

arXiv: https://arxiv.org/abs/1904.07442 · HTML: https://mlsanity.com/paper/1904.07442/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2019.

## Built on by (most cited first, 11 of 11)

- [Enriching Local and Global Contexts for Temporal Action Localization](https://mlsanity.com/paper/2107.12960/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Graph Convolutional Module for Temporal Action Localization in Videos](https://mlsanity.com/paper/2112.00302/) (2021)
- [LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception](https://mlsanity.com/paper/2210.15518/) (2022)
- [Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions](https://mlsanity.com/paper/2403.20254/) (2024)
- [Open-Vocabulary Action Localization with Iterative Visual Prompting](https://mlsanity.com/paper/2408.17422/) (2024)
- [Temporal Action Detection Model Compression by Progressive Block Drop](https://mlsanity.com/paper/2503.16916/) (2025)
- [Boundary Discretization and Reliable Classification Network for Temporal Action Detection](https://mlsanity.com/paper/2310.06403/) (2023)
- [A Hybrid Graph Network for Complex Activity Detection in Video](https://mlsanity.com/paper/2310.17493/) (2023)
- [Low Pass Filter for Anti-aliasing in Temporal Action Localization](https://mlsanity.com/paper/2104.11403/) (2021)
- [Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization](https://mlsanity.com/paper/2208.14856/) (2022)

## Abstract (arXiv)

Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and classification of each proposal through a fully shared backbone. However, such design of encapsulating all components of two subtasks in one single network might restrict the training by ignoring the specialized characteristic of each subtask. In this paper, we propose a novel Decoupled Single Shot temporal Action Detection (Decouple-SSAD) method to mitigate such problem by decoupling the localization and classification in a one-stage scheme. Particularly, two separate branches are designed in parallel to enable each component to own representations privately for accurate localization or classification. Each branch produces a set of action anchor layers by applying deconvolution to the feature maps of the main stream. Each branch produces a set of feature maps by applying deconvolution to the feature maps of the main stream. High-level semantic information from deeper layers is thus incorporated to enhance the feature representations. We conduct extensive experiments on THUMOS14 dataset and demonstrate superior performance over state-of-the-art methods. Our code is available online.