Informativity in Image Captions vs. Referring Expressions

no code implementations • PaM 2020 • Elizabeth Coppock, Danielle Dionne, Nathanial Graham, Elias Ganem, Shijie Zhao, Shawn Lin, Wenxing Liu, Derry Wijaya

We hope that an understanding of the systematic differences among these human datasets will ultimately allow them to be leveraged more effectively in the associated engineering tasks.

Image Captioning Object +3

Referring Expressions with Rational Speech Act Framework: A Probabilistic Approach

no code implementations • 16 May 2022 • Hieu Le, Taufiq Daryanto, Fabian Zhafransyah, Derry Wijaya, Elizabeth Coppock, Sang Chin

This paper focuses on a referring expression generation (REG) task in which the aim is to pick out an object in a complex visual scene.

Deep Learning Referring Expression +1