# A Pursuit of Temporal Accuracy in General Activity Detection

arXiv: https://arxiv.org/abs/1703.02716 · HTML: https://mlsanity.com/paper/1703.02716/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2017.

## Built on by (most cited first, 15 of 15)

- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [Self-Supervised Learning for Semi-Supervised Temporal Action Proposal](https://mlsanity.com/paper/2104.03214/) (2021)
- [Weakly Supervised Temporal Adjacent Network for Language Grounding](https://mlsanity.com/paper/2106.16136/) (2021)
- [Class Semantics-based Attention for Action Detection](https://mlsanity.com/paper/2109.02613/) (2021)
- [Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection](https://mlsanity.com/paper/2108.03619/) (2021)
- [Action Unit Memory Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2104.14135/) (2021)
- [Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation](https://mlsanity.com/paper/2103.16024/) (2021)
- [Self-Feedback DETR for Temporal Action Detection](https://mlsanity.com/paper/2308.10570/) (2023)
- [SVIP: Sequence VerIfication for Procedures in Videos](https://mlsanity.com/paper/2112.06447/) (2021)
- [Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection](https://mlsanity.com/paper/2303.17285/) (2023)
- [SimOn: A Simple Framework for Online Temporal Action Localization](https://mlsanity.com/paper/2211.04905/) (2022)
- [Temporal Action Localization Using Gated Recurrent Units](https://mlsanity.com/paper/2108.03375/) (2021)
- [Temporal Action Localization with Multi-temporal Scales](https://mlsanity.com/paper/2208.07493/) (2022)
- [Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization](https://mlsanity.com/paper/2507.06411/) (2025)

## Abstract (arXiv)

Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and completeness of a candidate instance. On two challenging temporal activity detection datasets, THUMOS14 and ActivityNet, the proposed framework significantly outperforms the existing state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling activities with various temporal structures.