Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Authors: Chaofan Huo, Ye Shi, Yuexin Ma, Lan Xu, Jingyi Yu, Jingya Wang
IJCAI 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results show that our method achieves impressive results on two challenging benchmarks, BEHAVE and Inter Cap datasets. |
| Researcher Affiliation | Academia | Chaofan Huo1,2 , Ye Shi1,2 , Yuexin Ma1,2 , Lan Xu1,2 , Jingyi Yu1,2 and Jingya Wang 1,2 1Shanghai Tech University 2Shanghai Engineering Research Center of Intelligent Vision and Imaging EMAIL |
| Pseudocode | No | The paper describes the methods in text and uses figures to illustrate the framework, but it does not contain any formal pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code has been publicly available at https://github.com/huochf/Stack FLOW. |
| Open Datasets | Yes | Dataset. We conduct experiments on two indoor datasets: BEHAVE [Bhatnagar et al., 2022] and Inter Cap [Huang et al., 2022b]. |
| Dataset Splits | No | The paper mentions 'We follow the of๏ฌcial train/test split to train and test our method' for BEHAVE and 'We randomly select 20% sequences for testing and the rest for training' for Inter Cap. It references 'validation' in the loss function, but does not specify a validation split or provide details on how the validation set was created or used for hyperparameter tuning. |
| Hardware Specification | Yes | The time is tested on a single NVIDIA Ge Force RTX 2080 Ti GPU. |
| Software Dependencies | No | The paper does not explicitly list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x, CUDA 11.x). |
| Experiment Setup | No | The paper describes the overall framework, loss functions, and optimization process, but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or other detailed system-level training settings in the main text. |