Seeing with Humans: Gaze-Assisted Neural Image Captioning
Abstract
Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art object and scene recognition models, bottom-up visual saliency, and human gaze. We then propose a novel split attention model for image captioning. Our model integrates human gaze information into an attention-based long short-term memory architecture, and allows the algorithm to allocate attention selectively to both fixated and non-fixated image regions. Through evaluation on the COCO/SALICON datasets we show that our method improves image captioning performance and that gaze can complement machine attention for semantic scene understanding tasks.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2016
- DOI:
- 10.48550/arXiv.1608.05203
- arXiv:
- arXiv:1608.05203
- Bibcode:
- 2016arXiv160805203S
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition