# Data Fusion for Deep Learning on Transport Mode Detection: A Case Study

arXiv: https://arxiv.org/abs/2106.05876 · HTML: https://mlsanity.com/paper/2106.05876/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 31 May 2021.

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

- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Selective Sensor Fusion for Neural Visual-Inertial Odometry](https://mlsanity.com/paper/1903.01534/) (2019)
- [Learn to Combine Modalities in Multimodal Deep Learning](https://mlsanity.com/paper/1805.11730/) (2018)
- [Multimodal Convolutional Neural Networks for Matching Image and Sentence](https://mlsanity.com/paper/1504.06063/) (2015)
- [Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving](https://mlsanity.com/paper/2002.00216/) (2020)

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

- [Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?](https://mlsanity.com/paper/2303.04204/) (2023)

## Abstract (arXiv)

In Transport Mode Detection, a great diversity of methodologies exist according to the choice made on sensors, preprocessing, model used, etc. In this domain, the comparisons between each option are not always complete. Experiments on a public, real-life dataset are led here to evaluate carefully each of the choices that were made, with a specific emphasis on data fusion methods. Our most surprising finding is that none of the methods we implemented from the literature is better than a simple late fusion. Two important decisions are the choice of a sensor and the choice of a representation for the data: we found that using 2D convolutions on spectrograms with a logarithmic axis for the frequencies was better than 1-dimensional temporal representations.