Temporal Constrained Feasible Subspace Learning for Human Pose Forecasting

Authors: Gaoang Wang, Mingli Song

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the proposed method on large-scale benchmarks, including Human3.6M, AMASS, and 3DPW. State-of-the-art performance has been achieved with the temporal constrained feasible solutions.
Researcher Affiliation Academia 1Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, China 2College of Computer Science and Technology, Zhejiang University, China
Pseudocode No The paper describes the proposed method conceptually and mathematically but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes Human3.6M [Ionescu et al., 2013] It is a large-scale dataset consisting of 3.6 million 3D human poses and corresponding images. ... AMASS [Mahmood et al., 2019] The Archive of Motion Capture as Surface Shapes (AMASS) dataset has been recently proposed with 18 existing Mo Cap datasets. ... 3DPW [von Marcard et al., 2018] The dataset consists of in-the-wild video sequences and 3D human poses captured by a moving camera.
Dataset Splits Yes Following the current literature [Mao et al., 2020; Mao et al., 2019; Martinez et al., 2017], we use subject 11 (S11) for validation, the subject 5 (S5) for testing, and all the rest of the subjects for training. ... Following [Mao et al., 2020; Sofianos et al., 2021], we take 13 datasets from AMASS in the experiment, with 8 datasets for training, 4 for validation and 1 for testing.
Hardware Specification Yes One NVIDIA RTX 3090 GPU is used for training.
Software Dependencies No The paper states: "We use Pytorch for training the neural networks and use ADAM [Kingma and Ba, 2014] as the optimizer." However, it does not provide specific version numbers for PyTorch, ADAM, or any other software components.
Experiment Setup Yes The learning rate is set to 0.01 and decayed by a factor of 0.1 every 5 epochs after the 20th epoch. The batch size is set to 256. The maximum epoch is set to 50. The constraint L is set to 50.