no code implementations • 31 Mar 2024 • Minyoung Oh, Duhyun Kim, Jae-Young Sim
Collecting and labeling real datasets to train the person search networks not only requires a lot of time and effort, but also accompanies privacy issues.
no code implementations • 15 Mar 2024 • Minyoung Oh, Jae-Young Sim
To this end, we devise the cross-model compatibility loss based on the contrastive learning with respect to the replay features across all the old datasets.
no code implementations • 4 Oct 2021 • Byeong-Ju Han, Kuhyeun Ko, Jae-Young Sim
The existing person search methods use the annotated labels of person identities to train deep networks in a supervised manner that requires a huge amount of time and effort for human labeling.
no code implementations • ICCV 2021 • Byeong-Ju Han, Kuhyeun Ko, Jae-Young Sim
Person search suffers from the conflicting objectives of commonness and uniqueness between the person detection and re-identification tasks that make the end-to-end training of person search networks difficult.
no code implementations • CVPR 2018 • Jae-Seong Yun, Jae-Young Sim
Large-scale 3D point clouds (LS3DPCs) captured by terrestrial LiDAR scanners often exhibit reflection artifacts by glasses, which degrade the performance of related computer vision techniques.
no code implementations • CVPR 2017 • Byeong-Ju Han, Jae-Young Sim
The images taken through glass often capture a target transmitted scene as well as undesired reflected scenes.
no code implementations • ICCV 2015 • Han-Ul Kim, Dae-Youn Lee, Jae-Young Sim, Chang-Su Kim
The patch weights represent the importance of each patch in the description of foreground information, and are used to construct an object descriptor, called spatially ordered and weighted patch (SOWP) descriptor.
no code implementations • CVPR 2015 • Chulwoo Lee, Won-Dong Jang, Jae-Young Sim, Chang-Su Kim
A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work.
no code implementations • CVPR 2015 • Dae-Youn Lee, Jae-Young Sim, Chang-Su Kim
The notion of multihypothesis trajectory analysis (MTA) for robust visual tracking is proposed in this work.
no code implementations • CVPR 2014 • Dae-Youn Lee, Jae-Young Sim, Chang-Su Kim
A novel visual tracking algorithm using patch-based appearance models is proposed in this paper.