# ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos

arXiv: https://arxiv.org/abs/2608.24043 · HTML: https://mlsanity.com/paper/2608.24043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 5 of 5)

- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2404.01518/) (2024)
- [SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation](https://mlsanity.com/paper/2105.14158/) (2021)
- [OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation](https://mlsanity.com/paper/2309.06276/) (2023)
- [Improving action segmentation via explicit similarity measurement](https://mlsanity.com/paper/2502.10713/) (2025)

## Abstract (arXiv)

Recognizing sequential construction activities is important for collaborative human-robot work; for example, robots are able to understand workers' current and upcoming actions and provide timely tool delivery or physical support. However, despite extensive research on construction worker activity recognition, existing studies have been limited to classifying activity categories, such as climbing, lifting, and walking, instead of recognizing fine-grained activity transitions from long-horizon sequences. Addressing this problem is challenging because annotating action temporal boundaries in long construction videos is time-consuming. In this study, we propose ConsensusTAS, a label-free, self-supervised learning approach to segment continuous video streams into distinct activity phases by exploiting the internal consensus of candidate segmentations. We evaluated our algorithm on three public datasets, where it outperformed state-of-the-art methods, achieving an F1@10 of 73.08 on GTEA, an F1@10 of 64.33 on Breakfast, and an F1@50 of 33.50 on static-camera videos from Assembly101. We also tested it on real-world construction videos, where post-hoc evaluation showed that the model successfully recognized and segmented actions within the composite activity of bricklaying, such as spreading mortar on a brick, placing the brick, pressing, and aligning. Compared with other temporal action segmentation models that require computationally intensive large vision-language models, our method can run on a CPU, which provides practical value for video surveillance and human-robot collaboration on mobile robotic platforms.