# OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation

arXiv: https://arxiv.org/abs/2309.06276 · HTML: https://mlsanity.com/paper/2309.06276/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 12 Sep 2023.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Visual Semantic Navigation using Scene Priors](https://mlsanity.com/paper/1810.06543/) (2018)
- [Unsupervised Learning from Narrated Instruction Videos](https://mlsanity.com/paper/1506.09215/) (2015)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Unsupervised learning of action classes with continuous temporal embedding](https://mlsanity.com/paper/1904.04189/) (2019)
- [Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment](https://mlsanity.com/paper/1803.10699/) (2018)
- [Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation](https://mlsanity.com/paper/2003.02824/) (2020)
- [Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling](https://mlsanity.com/paper/1703.08132/) (2017)
- [NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning](https://mlsanity.com/paper/1805.06875/) (2018)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [An end-to-end generative framework for video segmentation and recognition](https://mlsanity.com/paper/1509.01947/) (2015)
- [Unsupervised Learning and Segmentation of Complex Activities from Video](https://mlsanity.com/paper/1803.09490/) (2018)
- [Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation](https://mlsanity.com/paper/2103.11264/) (2021)
- [Weakly Supervised Energy-Based Learning for Action Segmentation](https://mlsanity.com/paper/1909.13155/) (2019)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Temporal Action Segmentation from Timestamp Supervision](https://mlsanity.com/paper/2103.06669/) (2021)
- [Weakly supervised learning of actions from transcripts](https://mlsanity.com/paper/1610.02237/) (2016)
- [Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences](https://mlsanity.com/paper/2001.11122/) (2020)
- [A Perceptual Prediction Framework for Self Supervised Event Segmentation](https://mlsanity.com/paper/1811.04869/) (2018)
- [Action Shuffle Alternating Learning for Unsupervised Action Segmentation](https://mlsanity.com/paper/2104.02116/) (2021)

## Built on by (most cited first, 11 of 11)

- [HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects](https://mlsanity.com/paper/2407.12371/) (2024)
- [CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2507.03539/) (2025)
- [2by2: Weakly-Supervised Learning for Global Action Segmentation](https://mlsanity.com/paper/2412.12829/) (2024)
- [Improving action segmentation via explicit similarity measurement](https://mlsanity.com/paper/2502.10713/) (2025)
- [From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings](https://mlsanity.com/paper/2511.21428/) (2025)
- [Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities](https://mlsanity.com/paper/2511.14945/) (2025)
- [ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation](https://mlsanity.com/paper/2604.26637/) (2026)
- [D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2608.05877/) (2026)
- [ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos](https://mlsanity.com/paper/2608.24043/) (2026)
- [VidParse: Online Parsing of Egocentric Procedures Like a Pro](https://mlsanity.com/paper/2608.27562/) (2026)
- [FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2608.29980/) (2026)

## Abstract (arXiv)

Temporal action segmentation is typically achieved by discovering the dramatic variances in global visual descriptors. In this paper, we explore the merits of local features by proposing the unsupervised framework of Object-centric Temporal Action Segmentation (OTAS). Broadly speaking, OTAS consists of self-supervised global and local feature extraction modules as well as a boundary selection module that fuses the features and detects salient boundaries for action segmentation. As a second contribution, we discuss the pros and cons of existing frame-level and boundary-level evaluation metrics. Through extensive experiments, we find OTAS is superior to the previous state-of-the-art method by 41% on average in terms of our recommended F1 score. Surprisingly, OTAS even outperforms the ground-truth human annotations in the user study. Moreover, OTAS is efficient enough to allow real-time inference.