# Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses

arXiv: https://arxiv.org/abs/2012.08236 · HTML: https://mlsanity.com/paper/2012.08236/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [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)
- [FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance](https://mlsanity.com/paper/2501.02430/) (2025)
- [AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation](https://mlsanity.com/paper/2309.00096/) (2023)
- [Audio-Visual Segmentation via Unlabeled Frame Exploitation](https://mlsanity.com/paper/2403.11074/) (2024)
- [Multi-modal Prompting for Low-Shot Temporal Action Localization](https://mlsanity.com/paper/2303.11732/) (2023)
- [Constraint and Union for Partially-Supervised Temporal Sentence Grounding](https://mlsanity.com/paper/2302.09850/) (2023)
- [Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models](https://mlsanity.com/paper/2407.11717/) (2024)
- [Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2412.00440/) (2024)
- [Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2212.09335/) (2022)
- [Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models](https://mlsanity.com/paper/2312.07408/) (2023)
- [DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2404.14890/) (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)
- [Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization](https://mlsanity.com/paper/2511.01588/) (2025)
- [Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting](https://mlsanity.com/paper/2403.14240/) (2024)
- [Squeeze Out Tokens from Sample for Finer-Grained Data Governance](https://mlsanity.com/paper/2503.14559/) (2025)
- [POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization](https://mlsanity.com/paper/2310.13585/) (2023)
- [Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation](https://mlsanity.com/paper/2511.01593/) (2025)
- [ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization](https://mlsanity.com/paper/2311.15916/) (2023)

## Abstract (arXiv)

Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse single-frame labels. However, such a framework inevitably suffers from a large solution space. This paper attempts to explore the proposal-based prediction paradigm for point-level annotations, which has the advantage of more constrained solution space and consistent predictions among neighboring frames. The point-level annotations are first used as the keypoint supervision to train a keypoint detector. At the location prediction stage, a simple but effective mapper module, which enables back-propagation of training errors, is then introduced to bridge the fully-supervised framework with weak supervision. To our best of knowledge, this is the first work to leverage the fully-supervised paradigm for the point-level setting. Experiments on THUMOS14, BEOID, and GTEA verify the effectiveness of our proposed method both quantitatively and qualitatively, and demonstrate that our method outperforms state-of-the-art methods.