Jae Sung (James) Park

I am a second year PhD student at University of Washington in Computer Science and Engineering advised by Yejin Choi and Ali Farhadi. My current research interests lie at the intersection of vision and language, specifically towards modeling visual cognition.

Previously, I received my B.S. degree in EECS at University of California, Berkeley, where I worked closely with Anna Rohrbach and Trevor Darrell .

Email  /  Google Scholar    

• New work on VisualCOMET: Visual Commonsense Reasoning in Time.
• Internship @ AI2 Mosaic Team in Winter 2020.
• Co-organized Large Scale Movie Description Challenge 2019 appeared in ICCV19 CLVL workshop.
• Started PhD at University of Washington in Fall 2019.

Can machines perform visual commonsense reasoning in time?
A new task that predicts person's intent and past and future events in images.

Link characters within a set of clips and generate descriptions with locally re-identified people.

Use discriminator to select the best video descriptions during inference.

Co-organizer

Teaching Assistant

Website Template taken from here and here.