Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze

Ece Takmaz, Sandro Pezzelle, Lisa Beinborn, Raquel Fernández

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review


When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting point a state-of-the-art image captioning system and develop several model variants that exploit information from human gaze patterns recorded during language production. In particular, we propose the first approach to image description generation where visual processing is modelled sequentially. Our experiments and analyses confirm that better descriptions can be obtained by exploiting gaze-driven attention and shed light on human cognitive processes by comparing different ways of aligning the gaze modality with language production. We find that processing gaze data sequentially leads to descriptions that are better aligned to those produced by speakers, more diverse, and more natural---particularly when gaze is encoded with a dedicated recurrent component.
Original languageEnglish
Title of host publicationProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
PublisherAssociation for Computational Linguistics
Number of pages14
Publication statusPublished - Nov 2020


Dive into the research topics of 'Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze'. Together they form a unique fingerprint.

Cite this