# Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer

arXiv: https://arxiv.org/abs/2504.14860 · HTML: https://mlsanity.com/paper/2504.14860/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 55 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 30 of 37)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [UntrimmedNets for Weakly Supervised Action Recognition and Detection](https://mlsanity.com/paper/1703.03329/) (2017)
- [Relaxed Transformer Decoders for Direct Action Proposal Generation](https://mlsanity.com/paper/2102.01894/) (2021)
- [Temporal Context Aggregation Network for Temporal Action Proposal Refinement](https://mlsanity.com/paper/2103.13141/) (2021)
- [TALLFormer: Temporal Action Localization with a Long-memory Transformer](https://mlsanity.com/paper/2204.01680/) (2022)
- [AutoLoc: Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1807.08333/) (2018)
- [Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2010.11594/) (2020)
- [ReAct: Temporal Action Detection with Relational Queries](https://mlsanity.com/paper/2207.07097/) (2022)
- [ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2203.15187/) (2022)
- [DCAN: Improving Temporal Action Detection via Dual Context Aggregation](https://mlsanity.com/paper/2112.03612/) (2021)
- [Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2107.12589/) (2021)
- [Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation](https://mlsanity.com/paper/2203.02925/) (2022)
- [BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection](https://mlsanity.com/paper/2205.02717/) (2022)
- [Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector](https://mlsanity.com/paper/1807.02929/) (2018)
- [RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization](https://mlsanity.com/paper/1904.00227/) (2019)
- [ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2103.15088/) (2021)
- [Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2305.17861/) (2023)
- [DyFADet: Dynamic Feature Aggregation for Temporal Action Detection](https://mlsanity.com/paper/2407.03197/) (2024)

## Built on by (most cited first, 6 of 6)

- [Evaluating and Steering Modality Preferences in Multimodal Large Language Model](https://mlsanity.com/paper/2505.20977/) (2025)
- [Length Matters: Length-Aware Transformer for Temporal Sentence Grounding](https://mlsanity.com/paper/2508.04299/) (2025)
- [GEM-TFL: Bridging Weak and Full Supervision for Forgery Localization through EM-Guided Decomposition and Temporal Refinement](https://mlsanity.com/paper/2603.05095/) (2026)
- [EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration](https://mlsanity.com/paper/2607.04472/) (2026)
- [CoRE: Weakly Supervised Coarse-to-Fine Risk Evidence Learning in Driving Videos](https://mlsanity.com/paper/2608.25344/) (2026)
- [Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2610.06234/) (2026)

## Abstract (arXiv)

Weakly-supervised Temporal Action Localization (WTAL) has achieved notable success but still suffers from a lack of temporal annotations, leading to a performance and framework gap compared with fully-supervised methods. While recent approaches employ pseudo labels for training, three key challenges: generating high-quality pseudo labels, making full use of different priors, and optimizing training methods with noisy labels remain unresolved. Due to these perspectives, we propose PseudoFormer, a novel two-branch framework that bridges the gap between weakly and fully-supervised Temporal Action Localization (TAL). We first introduce RickerFusion, which maps all predicted action proposals to a global shared space to generate pseudo labels with better quality. Subsequently, we leverage both snippet-level and proposal-level labels with different priors from the weak branch to train the regression-based model in the full branch. Finally, the uncertainty mask and iterative refinement mechanism are applied for training with noisy pseudo labels. PseudoFormer achieves state-of-the-art WTAL results on the two commonly used benchmarks, THUMOS14 and ActivityNet1.3. Besides, extensive ablation studies demonstrate the contribution of each component of our method.