MCM: Multi-condition Motion Synthesis Framework

Authors: Zeyu Ling, Bo Han, Yongkang Wong, Han Lin, Mohan Kankanhalli, Weidong Geng

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our method achieves competitive results in single-condition and multi-condition HMS tasks.
Researcher Affiliation Academia Zeyu Ling1 , Bo Han1 , Yongkang Wong2, Han Lin1, Mohan Kangkanhalli2 and Weidong Geng1 1College of Computer Science and Technology, Zhejiang University 2School of Computing, National University of Singapore
Pseudocode No The paper contains architectural diagrams (Figure 2, Figure 3) but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets Yes We evaluate the proposed method using the Human ML3D [Guo et al., 2022a], AIST++ [Li et al., 2021], and BEAT [Liu et al., 2022] dataset.
Dataset Splits No In the evaluation stage, prior studies were assessed using the complete dance motion sequences from the validation and test sets of AIST++ dataset... Table 1: Quantitative results on the Human ML3D test set. While validation and test sets are mentioned, specific details like percentages or sample counts for train/validation/test splits are not provided.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No We use CLIP [Radford et al., 2021] to extract features from text conditions. Similar to EDGE, we use the prior layer of Jukebox [Dhariwal et al., 2020] to extract features from all audio conditions... We employ the Adam optimizer for training the model... No specific version numbers for general software dependencies are provided.
Experiment Setup Yes Regarding the diffusion model, we set the number of diffusion steps at 1000, while the variances βt follow a linear progression from 0.0001 to 0.02. We employ the Adam optimizer for training the model, employing a learning rate of 0.0002 throughout both training phases. In concordance with MDM, we adopt the strategy of predicting xstart as an alternative to the prediction of noise.