Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.23409 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912096920272896 |
|---|---|
| author | D'Amelio, Alessandro Cartella, Giuseppe Cuculo, Vittorio Lucchi, Manuele Cornia, Marcella Cucchiara, Rita Boccignone, Giuseppe |
| author_facet | D'Amelio, Alessandro Cartella, Giuseppe Cuculo, Vittorio Lucchi, Manuele Cornia, Marcella Cucchiara, Rita Boccignone, Giuseppe |
| contents | Attention guides our gaze to fixate the proper location of the scene and holds it in that location for the deserved amount of time given current processing demands, before shifting to the next one. As such, gaze deployment crucially is a temporal process. Existing computational models have made significant strides in predicting spatial aspects of observer's visual scanpaths (where to look), while often putting on the background the temporal facet of attention dynamics (when). In this paper we present TPP-Gaze, a novel and principled approach to model scanpath dynamics based on Neural Temporal Point Process (TPP), that jointly learns the temporal dynamics of fixations position and duration, integrating deep learning methodologies with point process theory. We conduct extensive experiments across five publicly available datasets. Our results show the overall superior performance of the proposed model compared to state-of-the-art approaches. Source code and trained models are publicly available at: https://github.com/phuselab/tppgaze. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23409 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes D'Amelio, Alessandro Cartella, Giuseppe Cuculo, Vittorio Lucchi, Manuele Cornia, Marcella Cucchiara, Rita Boccignone, Giuseppe Computer Vision and Pattern Recognition Artificial Intelligence Attention guides our gaze to fixate the proper location of the scene and holds it in that location for the deserved amount of time given current processing demands, before shifting to the next one. As such, gaze deployment crucially is a temporal process. Existing computational models have made significant strides in predicting spatial aspects of observer's visual scanpaths (where to look), while often putting on the background the temporal facet of attention dynamics (when). In this paper we present TPP-Gaze, a novel and principled approach to model scanpath dynamics based on Neural Temporal Point Process (TPP), that jointly learns the temporal dynamics of fixations position and duration, integrating deep learning methodologies with point process theory. We conduct extensive experiments across five publicly available datasets. Our results show the overall superior performance of the proposed model compared to state-of-the-art approaches. Source code and trained models are publicly available at: https://github.com/phuselab/tppgaze. |
| title | TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.23409 |