Automatic generation of natural language descriptions of visual data: describing images and videos using recurrent and self-attentive models

Philipp Harzig. Automatic generation of natural language descriptions of visual data: describing images and videos using recurrent and self-attentive models. PhD thesis, University of Augsburg, Germany, 2022. [doi]

Authors

Philipp Harzig

This author has not been identified. Look up 'Philipp Harzig' in Google