# D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

arXiv: https://arxiv.org/abs/2012.06440 · HTML: https://mlsanity.com/paper/2012.06440/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [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)
- [Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation](https://mlsanity.com/paper/2203.02925/) (2022)
- [Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature](https://mlsanity.com/paper/2303.12332/) (2023)
- [Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2305.17861/) (2023)
- [Multi-modal Prompting for Low-Shot Temporal Action Localization](https://mlsanity.com/paper/2303.11732/) (2023)
- [Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels](https://mlsanity.com/paper/2304.07978/) (2023)
- [Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2212.09335/) (2022)
- [Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions](https://mlsanity.com/paper/2207.11805/) (2022)
- [Boosting Weakly-Supervised Temporal Action Localization with Text Information](https://mlsanity.com/paper/2305.00607/) (2023)
- [Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach](https://mlsanity.com/paper/2312.14138/) (2023)
- [Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction](https://mlsanity.com/paper/2501.11124/) (2025)
- [DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2307.16415/) (2023)
- [Open-Vocabulary Temporal Action Localization using Multimodal Guidance](https://mlsanity.com/paper/2406.15556/) (2024)
- [Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features](https://mlsanity.com/paper/2212.10596/) (2022)
- [Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning](https://mlsanity.com/paper/2206.11011/) (2022)
- [Action-Agnostic Point-Level Supervision for Temporal Action Detection](https://mlsanity.com/paper/2412.21205/) (2024)
- [Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization](https://mlsanity.com/paper/2207.06659/) (2022)
- [Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2308.12609/) (2023)
- [Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization](https://mlsanity.com/paper/2205.00400/) (2022)
- [POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization](https://mlsanity.com/paper/2310.13585/) (2023)
- [Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2305.04186/) (2023)
- [ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization](https://mlsanity.com/paper/2311.15916/) (2023)

## Abstract (arXiv)

This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a classification loss and utilizes a top-down attention mechanism to enhance the separability of latent foreground-background embeddings. The denoising loss term explicitly addresses the foreground-background noise in class activations by simultaneously maximizing intra-video and inter-video mutual information using a bottom-up attention mechanism. As a result, activations in the foreground regions are emphasized whereas those in the background regions are suppressed, thereby leading to more robust predictions. Comprehensive experiments are performed on multiple benchmarks, including THUMOS14 and ActivityNet1.2. Our D2-Net performs favorably in comparison to the existing methods on all datasets, achieving gains as high as 2.3% in terms of mAP at IoU=0.5 on THUMOS14. Source code is available at https://github.com/naraysa/D2-Net