Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition
Authors: Yingjie Chen, Diqi Chen, Tao Wang, Yizhou Wang, Yun Liang374-382
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of our CIS, and the model with CIS inserted, CISNet, has achieved state-of-the-art performance. |
| Researcher Affiliation | Academia | 1 School of Computer Science, Peking University, Beijing China 2 Advanced Institute of Information Technology (AIIT), Peking University, Hangzhou, China chenyingjie@pku.edu.cn, dqchen@aiit.org.cn, wangtao@pku.edu.cn, yizhou.wang@pku.edu.cn, ericlyun@pku.edu.cn |
| Pseudocode | No | The paper does not contain a clearly labeled pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | Yes | In our experiments, we use two AU benchmark datasets, BP4D (Zhang et al. 2014) and DISFA (Mavadati et al. 2013). |
| Dataset Splits | Yes | For each dataset, a subject-exclusive 3-fold crossvalidation is conducted, following the experiment settings mentioned in (Li et al. 2017, 2019; Song et al. 2021b) for a fair comparison. |
| Hardware Specification | Yes | All models are trained on one NVIDIA Tesla V100 16GB GPU. |
| Software Dependencies | No | The paper mentions Dlib and PyTorch but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | Yes | We use Stochastic Gradient Descent (SGD) with momentum of 0.9 and weight decay of 0.0005 as the optimizer. Learning rate is set to 0.001 and batch size is set to 4. The number of training epochs is set to 15, and early stopping strategy is employed for training. |