STRIVE: Scene Text Replacement In Videos

no code implementations • ICCV 2021 • Vijay Kumar B G, Jeyasri Subramanian, Varnith Chordia, Eugene Bart, Shaobo Fang, Kelly Guan, Raja Bala

Finally, the new text is transferred from the reference to remaining frames using a novel learned image transformation network that captures lighting and blur effects in a temporally consistent manner.

Style Transfer

Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation

no code implementations • 12 Mar 2021 • Zeman Shao, Shaobo Fang, Runyu Mao, Jiangpeng He, Janine Wright, Deborah Kerr, Carol Jo Boushey, Fengqing Zhu

We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting.

Image Segmentation Management +4

Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks

no code implementations • 27 Feb 2018 • Shaobo Fang, Zeman Shao, Runyu Mao, Chichen Fu, Deborah A. Kerr, Carol J. Boushey, Edward J. Delp, Fengqing Zhu

We can then estimate food energy based on the energy distribution.