# Marginalized Average Attentional Network for Weakly-Supervised Learning

arXiv: https://arxiv.org/abs/1905.08586 · HTML: https://mlsanity.com/paper/1905.08586/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

## Built on by (most cited first, 24 of 24)

- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Object-Region Video Transformers](https://mlsanity.com/paper/2110.06915/) (2021)
- [CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning](https://mlsanity.com/paper/2103.16392/) (2021)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2203.16800/) (2022)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2108.06524/) (2021)
- [Weakly Supervised Action Selection Learning in Video](https://mlsanity.com/paper/2105.02439/) (2021)
- [Colar: Effective and Efficient Online Action Detection by Consulting Exemplars](https://mlsanity.com/paper/2203.01057/) (2022)
- [ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2103.15088/) (2021)
- [ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2104.02967/) (2021)
- [ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2112.10977/) (2021)
- [The Blessings of Unlabeled Background in Untrimmed Videos](https://mlsanity.com/paper/2103.13183/) (2021)
- [Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context](https://mlsanity.com/paper/2103.16155/) (2021)
- [Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions](https://mlsanity.com/paper/2207.11805/) (2022)
- [Deep Motion Prior for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05607/) (2021)
- [Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2211.11324/) (2022)
- [Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling](https://mlsanity.com/paper/2308.09946/) (2023)
- [Contactless Oxygen Monitoring with Gated Transformer](https://mlsanity.com/paper/2212.03357/) (2022)
- [Action Shuffling for Weakly Supervised Temporal Localization](https://mlsanity.com/paper/2105.04208/) (2021)
- [Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2105.14430/) (2021)

## Abstract (arXiv)

In weakly-supervised temporal action localization, previous works have failed to locate dense and integral regions for each entire action due to the overestimation of the most salient regions. To alleviate this issue, we propose a marginalized average attentional network (MAAN) to suppress the dominant response of the most salient regions in a principled manner. The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion. MAA samples multiple subsets from the video snippet features according to a set of latent discriminative probabilities and takes the expectation over all the averaged subset features. Theoretically, we prove that the MAA module with learned latent discriminative probabilities successfully reduces the difference in responses between the most salient regions and the others. Therefore, MAAN is able to generate better class activation sequences and identify dense and integral action regions in the videos. Moreover, we propose a fast algorithm to reduce the complexity of constructing MAA from O(2T) to O(T2). Extensive experiments on two large-scale video datasets show that our MAAN achieves superior performance on weakly-supervised temporal action localization