# Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

arXiv: https://arxiv.org/abs/2312.14138 · HTML: https://mlsanity.com/paper/2312.14138/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 72 references that are in the map.
- First posted on arXiv 21 Dec 2023.

## Builds on (most cited first, 30 of 48)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization](https://mlsanity.com/paper/1704.04232/) (2017)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [UntrimmedNets for Weakly Supervised Action Recognition and Detection](https://mlsanity.com/paper/1703.03329/) (2017)
- [Weakly Supervised Action Localization by Sparse Temporal Pooling Network](https://mlsanity.com/paper/1712.05080/) (2017)
- [W-TALC: Weakly-supervised Temporal Activity Localization and Classification](https://mlsanity.com/paper/1807.10418/) (2018)
- [Deep Comprehensive Correlation Mining for Image Clustering](https://mlsanity.com/paper/1904.06925/) (2019)
- [AutoLoc: Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1807.08333/) (2018)
- [Deep Spectral Clustering using Dual Autoencoder Network](https://mlsanity.com/paper/1904.13113/) (2019)
- [CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning](https://mlsanity.com/paper/2103.16392/) (2021)
- [Weakly-supervised Action Localization with Background Modeling](https://mlsanity.com/paper/1908.06552/) (2019)
- [Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2010.11594/) (2020)
- [3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization](https://mlsanity.com/paper/1908.08216/) (2019)
- [Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination](https://mlsanity.com/paper/2008.03813/) (2020)
- [Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning](https://mlsanity.com/paper/2004.00163/) (2020)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization](https://mlsanity.com/paper/2007.06643/) (2020)
- [ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2203.15187/) (2022)
- [Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2107.12589/) (2021)

## Built on by (most cited first, 8 of 8)

- [Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models](https://mlsanity.com/paper/2411.08466/) (2024)
- [Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction](https://mlsanity.com/paper/2501.11124/) (2025)
- [Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network](https://mlsanity.com/paper/2505.01880/) (2025)
- [Action-Agnostic Point-Level Supervision for Temporal Action Detection](https://mlsanity.com/paper/2412.21205/) (2024)
- [Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2407.08971/) (2024)
- [CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization](https://mlsanity.com/paper/2505.23524/) (2025)
- [Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification](https://mlsanity.com/paper/2408.07467/) (2024)
- [An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering](https://mlsanity.com/paper/2509.20976/) (2025)

## Abstract (arXiv)

Weakly-supervised temporal action localization aims to localize action instances in videos with only video-level action labels. Existing methods mainly embrace a localization-by-classification pipeline that optimizes the snippet-level prediction with a video classification loss. However, this formulation suffers from the discrepancy between classification and detection, resulting in inaccurate separation of foreground and background (F&B) snippets. To alleviate this problem, we propose to explore the underlying structure among the snippets by resorting to unsupervised snippet clustering, rather than heavily relying on the video classification loss. Specifically, we propose a novel clustering-based F&B separation algorithm. It comprises two core components: a snippet clustering component that groups the snippets into multiple latent clusters and a cluster classification component that further classifies the cluster as foreground or background. As there are no ground-truth labels to train these two components, we introduce a unified self-labeling mechanism based on optimal transport to produce high-quality pseudo-labels that match several plausible prior distributions. This ensures that the cluster assignments of the snippets can be accurately associated with their F&B labels, thereby boosting the F&B separation. We evaluate our method on three benchmarks: THUMOS14, ActivityNet v1.2 and v1.3. Our method achieves promising performance on all three benchmarks while being significantly more lightweight than previous methods. Code is available at https://github.com/Qinying-Liu/CASE