# "Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living

arXiv: https://arxiv.org/abs/2306.13149 · HTML: https://mlsanity.com/paper/2306.13149/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 58 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 8 of 8)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [Zero-Shot Activity Recognition with Verb Attribute Induction](https://mlsanity.com/paper/1707.09468/) (2017)
- [Learning Attribute Representation for Human Activity Recognition](https://mlsanity.com/paper/1802.00761/) (2018)
- [New efficient algorithms for multiple change-point detection with kernels](https://mlsanity.com/paper/1710.04556/) (2017)
- [Accoustate: Auto-annotation of IMU-generated Activity Signatures under Smart Infrastructure](https://mlsanity.com/paper/2112.06651/) (2021)

## Abstract (arXiv)

Complex activities of daily living (ADLs) often consist of multiple micro-activities. When performed sequentially, these micro-activities help the user accomplish the broad macro-activity. Naturally, a deeper understanding of these micro-activities can help develop more sophisticated human activity recognition (HAR) models and add explainability to their inferred conclusions. Previous research has attempted to achieve this by utilizing fine-grained annotated data that provided the required supervision and rules for associating the micro-activities to identify the macro-activity. However, this ``bottom-up'' approach is unrealistic as getting such high-quality, fine-grained annotated sensor datasets is challenging, costly, and time-consuming. Understanding this, in this paper, we develop AmicroN, which adapts a ``top-down'' approach by exploiting coarse-grained annotated data to expand the macro-activities into their constituent micro-activities without any external supervision. In the backend, AmicroN uses textitunsupervised change-point detection to search for the micro-activity boundaries across a complex ADL. Then, it applies a textitgeneralized zero-shot approach to characterize it. We evaluate AmicroN on two real-life publicly available datasets and observe that AmicroN can identify the micro-activities with micro Ftextsubscript1-score >0.75 for both datasets. Additionally, we also perform an initial proof-of-concept on leveraging the state-of-the-art (SOTA) large language models (LLMs) with attribute embeddings predicted by AmicroN to enhance further the explainability surrounding the detection of micro-activities.