Denoising Diffusion Models are Good General Gaze Feature Learners

Authors: Guanzhong Zeng, Jingjing Wang, Pengwei Yin, Zefu Xu, Mingyang Zhou

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate denoising diffusion models are also good general gaze feature learners. ... 5 Experiments
Researcher Affiliation Collaboration 1Hikvision Research Institute 2Shenzhen University
Pseudocode No The paper describes methods in paragraph text and uses diagrams, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes Gaze Diff is a general self-supervised representation learning framework. Therefore, we use the following datasets in our experiments as previous methods do: ETH-XGaze [Zhang et al., 2020], EVE [Park et al., 2020], Gaze360 [Kellnhofer et al., 2019], Gaze Capture [Krafka et al., 2016], Columbia Gaze [Smith et al., 2013], MPIIFace Gaze [Zhang et al., 2017b], Eye Diap [Funes Mora et al., 2014] and VGG-Face2 [Cao et al., 2018].
Dataset Splits Yes For the self-supervised methods, we pre-train in DX, then freeze the pre-trained learner G and add a FC layer as gaze regressor M for linear-probe analysis following [Chen et al., 2020]. We use different proportions of annotated training data to adapt M and evaluate on the separate validation data. ... Specifically, we use the leave-one-out (15-fold) and 5-fold cross-validation for DD and DO. In each fold, we randomly select 50 samples with labels to fine-tune M and repeat each experiment for 10 times.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU models, CPU types, memory amounts) used for running the experiments in the main text.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python 3.8, PyTorch 1.9, CUDA 11.1) needed to replicate the experiments.
Experiment Setup No The paper mentions training models and fine-tuning, but does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs), optimizer settings, or other system-level training configurations in the main text.