Learning a Generalized Gaze Estimator from Gaze-Consistent Feature
Authors: Mingjie Xu, Haofei Wang, Feng Lu
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that our proposed method achieves state-of-the-art performance on gaze domain generalization task. Furthermore, our proposed method also improves domain adaption performance on gaze estimation. |
| Researcher Affiliation | Academia | 1State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University 2Peng Cheng Laboratory, Shenzhen, China {xumingjie, lufeng}@buao.edu.cn, wanghf@pcl.ac.cn |
| Pseudocode | Yes | Algorithm 1 describes the training procedure of our proposed method. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing the code for the methodology or a link to a code repository. |
| Open Datasets | Yes | In this paper, we use 4 commonly-used gaze datasets, i.e., ETH-XGaze (DE) (Zhang et al. 2020), Gaze360 (DG) (Kellnhofer et al. 2019), MPIIGaze (DM) (Zhang et al. 2017a) and Eye Diap (DD) (Funes Mora, Monay, and Odobez 2014). |
| Dataset Splits | Yes | ETH-XGaze contains 80 subjects, and we use data from 75 subjects for training (713646 images) and the rest 5 subjects data for validation. |
| Hardware Specification | No | The paper states: "We use a single NVIDIA GPU to run the experiments." This is not specific enough to identify the exact GPU model or other hardware components required for a 'Yes' answer. |
| Software Dependencies | No | The paper mentions using "Res Net-18 (He et al. 2016) as backbone" and "Adam optimizer", and implicitly "Py Torch". However, it does not provide specific version numbers for these software components, which is required for a 'Yes' answer. |
| Experiment Setup | Yes | All the images are resized to 224x224 and normalized to [0, 1]. The batch size is 128, and we train the model for 10 epochs for ETH-XGaze and 100 epochs for Gaze360. We use Adam optimizer with a learning rate of 10^-4, and set β1 = 0.9, β2 = 0.95. |