In this paper, we describe a new multimodal dataset that consists of gaze measurements and spoken descriptions collected in parallel during an image inspection ...
SNAG is a multimodal dataset consisting of co-collected eye movements and spoken descriptions produced during an image-inspection task. This dataset was ...
SNAG: Spoken Narratives and Gaze Dataset | Papers With Code
paperswithcode.com › paper › snag-spok...
In this paper, we describe a new multimodal dataset that consists of gaze measurements and spoken descriptions collected in parallel during an image inspection ...
A new multimodal dataset that consists of gaze measurements and spoken descriptions collected in parallel during an image inspection task is described and ...
Preethi Vaidyanathan, Emily Tucker Prud'hommeaux, Jeff B. Pelz, Cecilia Ovesdotter Alm : SNAG: Spoken Narratives and Gaze Dataset. ACL (2) 2018: 132-137.
Annotating images via speaking and pointing has multiple strong advantages: (i) it leads to significant speed gains, as saying the class names is fast: ...
We propose a framework that integrates human-elicited gaze and spoken language to label perceptually important regions in an image.
We propose a framework that integrates human-elicited gaze and spoken language to label perceptually important regions in an image.
We share the information about recent multimodal datasets which are available for research purposes.
Publications | Computational Linguistics and Speech Processing ...
www.rit.edu › clasp › publications
SNAG: Spoken narratives and gaze dataset. Preethi Vaidyanathan, Emily T ... From spoken narratives to domain knowledge: Mining linguistic data for medical image ...