Dae Hwi Choi — accepted AI-conference papers

2022

Robust Thermal Infrared Pedestrian Detection By Associating Visible Pedestrian Knowledge

Sungjune Park, Dae Hwi Choi, Jung Uk Kim, Yong Man Ro

ICASSP 2022accepted

Recently, pedestrian detection on thermal infrared images has shown the robust pedestrian detection performance. In this paper, we propose a novel thermal infrared pedestrian detection framework which can associate and utilize the complementary pedestrian knowledge from visible images. Motivated by…

Cited by 0 Source ↗Scholar ↗

2021

Video Prediction Recalling Long-Term Motion Context via Memory Alignment Learning

Sangmin Lee, Hak Gu Kim, Dae Hwi Choi, Hyung-Il Kim, Yong Man Ro

CVPR 2021poster

Our work addresses long-term motion context issues for predicting future frames. To predict the future precisely, it is required to capture which long-term motion context (e.g., walking or running) the input motion (e.g., leg movement) belongs to. The bottlenecks arising when dealing with the long-t…

Cited by 146 PDF ↗code ↗Scholar ↗