# EmbraceNet for Activity: A Deep Multimodal Fusion Architecture for Activity Recognition

arXiv: https://arxiv.org/abs/2004.13918 · HTML: https://mlsanity.com/paper/2004.13918/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [SFusion: Self-attention based N-to-One Multimodal Fusion Block](https://mlsanity.com/paper/2208.12776/) (2022)
- [Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion](https://mlsanity.com/paper/2309.14398/) (2023)
- [Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2203.04153/) (2022)
- [Feature Pyramid biLSTM: Using Smartphone Sensors for Transportation Mode Detection](https://mlsanity.com/paper/2310.11087/) (2023)
- [A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation](https://mlsanity.com/paper/2107.07331/) (2021)
- [Transportation mode recognition based on low-rate acceleration and location signals with an attention-based multiple-instance learning network](https://mlsanity.com/paper/2404.15323/) (2024)

## Abstract (arXiv)

Human activity recognition using multiple sensors is a challenging but promising task in recent decades. In this paper, we propose a deep multimodal fusion model for activity recognition based on the recently proposed feature fusion architecture named EmbraceNet. Our model processes each sensor data independently, combines the features with the EmbraceNet architecture, and post-processes the fused feature to predict the activity. In addition, we propose additional processes to boost the performance of our model. We submit the results obtained from our proposed model to the SHL recognition challenge with the team name "Yonsei-MCML."