# Watch-n-Patch: Unsupervised Learning of Actions and Relations

arXiv: https://arxiv.org/abs/1603.03541 · HTML: https://mlsanity.com/paper/1603.03541/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2016.

## Built on by (most cited first, 1 of 1)

- [Classification of Primitive Manufacturing Tasks from Filtered Event Data](https://mlsanity.com/paper/2303.09558/) (2023)

## Abstract (arXiv)

There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple basic level actions in a completely unsupervised setting. Our model learns high-level co-occurrence and temporal relations between the actions. We consider the video as a sequence of short-term action clips, which contains human-words and object-words. An activity is about a set of action-topics and object-topics indicating which actions are present and which objects are interacting with. We then propose a new probabilistic model relating the words and the topics. It allows us to model long-range action relations that commonly exist in the composite activities, which is challenging in previous works. We apply our model to the unsupervised action segmentation and clustering, and to a novel application that detects forgotten actions, which we call action patching. For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects. Moreover, we develop a robotic system that watches people and reminds people by applying our action patching algorithm. Our robotic setup can be easily deployed on any assistive robot.