Global ETD Search

Leveraging Multimodal Perspectives to Learn Common Sense for Vision and Language Tasks

Lin, XiaoVirginia Tech2017

… Humans have the remarkable ability to interpret images and text from different perspectives in multiple modalities, and to use large amounts of commonsense knowledge while performing visual or textual tasks. Inspired by that ability, we approach commonsense learning as leveraging perspectives …

vt Repository record for Leveraging Multimodal Perspectives to Learn Common Sense for Vision and Language Tasks (opens in a new tab)