MotionMixer: MLP-based 3D Human Body Pose Forecasting
Authors: Arij Bouazizi, Adrian Holzbock, Ulrich Kressel, Klaus Dietmayer, Vasileios Belagiannis
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our approach on Human3.6M, AMASS, and 3DPW datasets using the standard evaluation protocols. For all evaluations, we demonstrate state-of-the-art performance, while having a model with a smaller number of parameters. |
| Researcher Affiliation | Collaboration | 1Mercedes-Benz AG, Stuttgart, Germany 2Ulm University, Ulm, Germany 3Otto von Guericke University Magdeburg, Magdeburg, Germany |
| Pseudocode | No | The paper includes figures and mathematical formulations, but does not contain explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | Our code is available at: https://github.com/MotionMLP/MotionMixer. |
| Open Datasets | Yes | Human3.6M. [Ionescu et al., 2013]... AMASS. [Mahmood et al., 2019]... 3DPW. The 3D Pose in the Wild dataset [von Marcard et al., 2018] |
| Dataset Splits | Yes | Human3.6M. Following [Sofianos et al., 2021; Mao et al., 2020], we use the subject (S11) for validation, (S5) for testing, and the rest of the subjects for training. AMASS. Following [Sofianos et al., 2021; Mao et al., 2021], we select 8 datasets for training, 4 for validation, and one (BMLrub) as the test set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments (e.g., GPU/CPU models, memory, or cloud instance types). |
| Software Dependencies | No | The paper mentions using 'Adam' as an optimizer but does not specify version numbers for any key software components or libraries. |
| Experiment Setup | Yes | In each MLP block, a dropout layer with a rate of 0.1 is added to prevent overfitting. We use Adam [Kingma and Ba, 2014] as the optimizer. During training, the learning rate is set to 10-2 and decayed by a factor of 0.1 every 10 epochs. We train our model for 50 epochs with a batch size of 50 for Human3.6M and 256 for AMASS. |