SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation
This work addresses the challenge of analyzing gaze behavior for cultural heritage preservation, though it is incremental as it adapts existing techniques to a new domain.
The paper tackled the problem of predicting human eye movement sequences (scanpaths) when viewing paintings by introducing SPGen, a deep learning model that uses unsupervised domain adaptation to transfer knowledge from natural scenes to artworks, and it outperformed existing methods.
Understanding human visual attention is key to preserving cultural heritage We introduce SPGen a novel deep learning model to predict scanpaths the sequence of eye movementswhen viewers observe paintings. Our architecture uses a Fully Convolutional Neural Network FCNN with differentiable fixation selection and learnable Gaussian priors to simulate natural viewing biases To address the domain gap between photographs and artworks we employ unsupervised domain adaptation via a gradient reversal layer allowing the model to transfer knowledge from natural scenes to paintings Furthermore a random noise sampler models the inherent stochasticity of eyetracking data. Extensive testing shows SPGen outperforms existing methods offering a powerful tool to analyze gaze behavior and advance the preservation and appreciation of artistic treasures.