no code implementations • 19 Oct 2022 • Donghwa Kang, Seunghoon Lee, Hoon Sung Chwa, Seung-Hwan Bae, Chang Mook Kang, Jinkyu Lee, Hyeongboo Baek
Focusing on multiple choices of a workload pair of detection and association, which are two main components of the tracking-by-detection approach for MOT, we tailor a measure of object confidence for RT-MOT and develop how to estimate the measure for the next frame of each MOT task.
no code implementations • 17 Nov 2020 • Seong-Ho Lee, Seung-Hwan Bae
In this paper, we propose a novel generator for super-resolving features of the convolutional object detectors.
1 code implementation • 24 Jan 2019 • Seung-Hwan Bae
However, the detection accuracy is degraded often because of the low discriminability of object CNN features caused by occlusions and inaccurate region proposals.
no code implementations • 1 Dec 2017 • Seung-Hwan Bae, Youngwan Lee, Youngjoo Jo, Yuseok Bae, Joong-won Hwang
The recent advances of convolutional detectors show impressive performance improvement for large scale object detection.
no code implementations • CVPR 2014 • Seung-Hwan Bae, Kuk-Jin Yoon
We first propose the tracklet confidence using the detectability and continuity of a tracklet, and formulate a multi-object tracking problem based on the tracklet confidence.