Heatmap Distribution Matching for Human Pose Estimation
Authors: Haoxuan Qu, Li Xu, Yujun Cai, Lin Geng Foo, Jun Liu
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset. |
| Researcher Affiliation | Academia | Haoxuan Qu SUTD Singapore haoxuan_qu@mymail.sutd.edu.sg Li Xu SUTD Singapore li_xu@mymail.sutd.edu.sg Yujun Cai NTU Singapore yujun001@e.ntu.edu.sg Lin Geng Foo SUTD Singapore lingeng_foo@mymail.sutd.edu.sg Jun Liu SUTD Singapore jun_liu@sutd.edu.sg |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper includes a self-reflection question: "Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [No]" |
| Open Datasets | Yes | To evaluate the effectiveness of our proposed method, we conduct experiments on the COCO dataset [16] and the MPII Human Pose dataset [1]. |
| Dataset Splits | Yes | This dataset has three subsets including COCO training set, COCO validation set, and COCO test-dev set, which have 57k, 5k and 20k images, respectively. We conduct experiments on this dataset via first training the model on the train2017 set, and then evaluating the model on the val2017 set and test-dev2017 set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used, such as GPU or CPU models. It states: "Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [No]" |
| Software Dependencies | No | The paper mentions the use of the Sinkhorn algorithm but does not specify any software libraries or their version numbers (e.g., PyTorch version, Python version). |
| Experiment Setup | Yes | To calculate the Earth Mover s Distance using the Sinkhorn algorithm, we set the Sinkhorn entropic regularization parameter to 1 and the number of Sinkhorn iterations to 1000 in our experiments. |