MotionTransformer: Transferring Neural Inertial Tracking between Domains
Authors: Changhao Chen, Yishu Miao, Chris Xiaoxuan Lu, Linhai Xie, Phil Blunsom, Andrew Markham, Niki Trigoni8009-8016
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through the experiments, we demonstrate that it is able to efficiently and effectively convert the raw sequence from a new unlabelled target domain into an accurate inertial trajectory, benefiting from the motion knowledge transferred from the labelled source domain. We also conduct real-world experiments to show our framework can reconstruct physically meaningful trajectories from raw IMU measurements obtained with a standard mobile phone in various attachments. |
| Researcher Affiliation | Collaboration | Changhao Chen,1 Yishu Miao,1 Chris Xiaoxuan Lu,1 Linhai Xie,1 Phil Blunsom,1,2 Andrew Markham,1 Niki Trigoni1 1Department of Computer Science, University of Oxford 2Deep Mind firstname.lastname@cs.ox.ac.uk |
| Pseudocode | No | The paper describes the model architecture and mathematical formulations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any link or explicit statement about the availability of open-source code for the described methodology. |
| Open Datasets | Yes | In summary, the dataset1 (Chen et al. 2018b) used in this work contains around 45K, 53 K, 36K and 29K sequences for handheld, pocket, bag, trolley domains respectively. Dataset can be found at http://deepio.cs.ox.ac.uk |
| Dataset Splits | Yes | In summary, the dataset1 (Chen et al. 2018b) used in this work contains around 45K, 53 K, 36K and 29K sequences for handheld, pocket, bag, trolley domains respectively. Among them, 4K sequences were selected as validation data in each domain, and the rest was taken as training set. |
| Hardware Specification | No | The paper mentions 'a commercial-off-the-shelf smartphone, the iPhone 7Plus' for data collection, but does not specify the hardware (e.g., CPU, GPU, memory) used for running the experiments or training the models. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, frameworks). |
| Experiment Setup | Yes | In our training phase, we set the hyper-parameters λ1 = 0.01, λ2 = 100, λ3 = 0.1, and λ4 = 1. |