My name is Jisoo Jeong. I am a Staff Engineer at Qualcomm AI Research. I received my Ph.D. degree at Seoul National University in 2021, advised by Prof. Nojun Kwak. I have researched Semi-supervised learning and Object detection and applied conventional semi-supervised learning methods to object detection algorithms. In recent years, I have been working on correspondence tasks, including optical flow and stereo-depth estimation.
Email : jisojeon@qti.qualcomm.com
Github : https://github.com/soo89
Scholar : Scholar
Resume : CV
Optical Flow
OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
Jisoo Jeong, Hong Cai, Risheek Garrepalli, Jamie Menjay Lin, Munawar Hayat, Fatih Porikli
CVPR 2024
DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling
Jisoo Jeong, Hong Cai, Risheek Garrepalli, Fatih Porikli
CVPR 2023
Imposing Consistency for Optical Flow Estimation
Jisoo Jeong, Jamie Menjay Lin, Fatih Porikli, Nojun Kwak
CVPR 2022
Object Detection
Interpolation-based Semi-supervised Learning for Object detection
Jisoo Jeong, Vikas Verma, Minsung Hyun, Juho Kannala, Nojun Kwak
CVPR 2021
Tell Me What They're Holding: Weakly-Supervised Object Detection with Transferable Knowledge from Human-object Interaction
Daesic Kim*, Gyujeong Lee*, Jisoo Jeong*, Nojun Kwak
AAAI 2020
Consistency-based Semi-supervised Learning for Object detection
Jisoo Jeong*, Seungeui Lee*, Jeesoo Kim, Nojun Kwak
NeurIPS 2019
Enhancement of SSD by concatenating feature maps for object detection
Jisoo Jeong, Hyojin Park, Nojun Kwak
BMVC 2017