# Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering

arXiv: https://arxiv.org/abs/2105.13353 · HTML: https://mlsanity.com/paper/2105.13353/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 93 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 30 of 70)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Learning Representations for Automatic Colorization](https://mlsanity.com/paper/1603.06668/) (2016)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [Graph Convolutional Networks for Temporal Action Localization](https://mlsanity.com/paper/1909.03252/) (2019)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [Local Aggregation for Unsupervised Learning of Visual Embeddings](https://mlsanity.com/paper/1903.12355/) (2019)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [Colorization as a Proxy Task for Visual Understanding](https://mlsanity.com/paper/1703.04044/) (2017)
- [Video Representation Learning by Dense Predictive Coding](https://mlsanity.com/paper/1909.04656/) (2019)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles](https://mlsanity.com/paper/1811.09795/) (2018)
- [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017)

## Built on by (most cited first, 30 of 49)

- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2404.01518/) (2024)
- [Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey](https://mlsanity.com/paper/2305.05080/) (2023)
- [Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments](https://mlsanity.com/paper/2207.10785/) (2022)
- [Hierarchical Vector Quantization for Unsupervised Action Segmentation](https://mlsanity.com/paper/2412.17640/) (2024)
- [Timestamp-Supervised Action Segmentation with Graph Convolutional Networks](https://mlsanity.com/paper/2206.15031/) (2022)
- [Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment](https://mlsanity.com/paper/2305.19478/) (2023)
- [United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos](https://mlsanity.com/paper/2311.03550/) (2023)
- [OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation](https://mlsanity.com/paper/2309.06276/) (2023)
- [Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization](https://mlsanity.com/paper/2409.07967/) (2024)
- [Joint Self-Supervised Video Alignment and Action Segmentation](https://mlsanity.com/paper/2503.16832/) (2025)
- [Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos](https://mlsanity.com/paper/2303.12370/) (2023)
- [Leveraging triplet loss for unsupervised action segmentation](https://mlsanity.com/paper/2304.06403/) (2023)
- [Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding](https://mlsanity.com/paper/2403.11463/) (2024)
- [OnlineTAS: An Online Baseline for Temporal Action Segmentation](https://mlsanity.com/paper/2411.01122/) (2024)
- [HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos](https://mlsanity.com/paper/2505.12911/) (2025)
- [Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion](https://mlsanity.com/paper/2309.06462/) (2023)
- [CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2507.03539/) (2025)
- [Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation](https://mlsanity.com/paper/2508.04513/) (2025)
- [Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport](https://mlsanity.com/paper/2507.15540/) (2025)
- [Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion](https://mlsanity.com/paper/2305.19480/) (2023)
- [2by2: Weakly-Supervised Learning for Global Action Segmentation](https://mlsanity.com/paper/2412.12829/) (2024)
- [Live and Learn: Continual Action Clustering with Incremental Views](https://mlsanity.com/paper/2404.07962/) (2024)
- [Pose-Aware Weakly-Supervised Action Segmentation](https://mlsanity.com/paper/2504.05700/) (2025)
- [End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning](https://mlsanity.com/paper/2309.15683/) (2023)
- [Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains](https://mlsanity.com/paper/2311.18773/) (2023)
- [SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation](https://mlsanity.com/paper/2312.12347/) (2023)
- [Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models](https://mlsanity.com/paper/2406.16638/) (2024)
- [Improving action segmentation via explicit similarity measurement](https://mlsanity.com/paper/2502.10713/) (2025)
- [Looking into the Unknown: Exploring Action Discovery for Segmentation of Known and Unknown Actions](https://mlsanity.com/paper/2508.05529/) (2025)

## Abstract (arXiv)

We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where representation learning and clustering are often performed sequentially. We leverage temporal information in videos by employing temporal optimal transport. In particular, we incorporate a temporal regularization term which preserves the temporal order of the activity into the standard optimal transport module for computing pseudo-label cluster assignments. The temporal optimal transport module enables our approach to learn effective representations for unsupervised activity segmentation. Furthermore, previous methods require storing learned features for the entire dataset before clustering them in an offline manner, whereas our approach processes one mini-batch at a time in an online manner. Extensive evaluations on three public datasets, i.e. 50-Salads, YouTube Instructions, and Breakfast, and our dataset, i.e., Desktop Assembly, show that our approach performs on par with or better than previous methods, despite having significantly less memory constraints. Our code and dataset are available on our research website: https://retrocausal.ai/research/