Jae Sung (James) Park

I am a first 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    

profile photo
  News
Research
sym VisualCOMET: Reasoning about the Dynamic Context of a Still Image
Jae Sung Park, Chandra Bhagavatula, Roozbeh Mottaghi, Ali Farhadi, Yejin Choi
ECCV, 2020 (Spotlight)
project page / arXiv / code

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

sym Identity Aware Multi-Sentence Video Description
Jae Sung Park, Trevor Darrell, Anna Rohrbach
ECCV, 2020
project page

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

sym Adversarial Inference for Multi-Sentence Video Description
Jae Sung Park, Marcus Rohrbach, Trevor Darrell, Anna Rohrbach
CVPR, 2019 (Oral)
arxiv / code

Use discriminator to select the best video descriptions during inference.

Service
sym Large Scale Movie Description Challenge 2019

Co-organizer



sym CSE 599/G1: Intro to Deep Learning, Fall 2019

Teaching Assistant




Website Template taken from here and here.