Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Chang, Gyusam"'
Autor:
Chang, Gyusam, Lee, Jiwon, Kim, Donghyun, Kim, Jinkyu, Lee, Dongwook, Ji, Daehyun, Jang, Sujin, Kim, Sangpil
Recent advances in 3D object detection leveraging multi-view cameras have demonstrated their practical and economical value in various challenging vision tasks. However, typical supervised learning approaches face challenges in achieving satisfactory
Externí odkaz:
http://arxiv.org/abs/2410.22461
Autor:
Chang, Gyusam, Roh, Wonseok, Jang, Sujin, Lee, Dongwook, Ji, Daehyun, Oh, Gyeongrok, Park, Jinsun, Kim, Jinkyu, Kim, Sangpil
Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD models more gen
Externí odkaz:
http://arxiv.org/abs/2403.03721
Autor:
Roh, Wonseok, Chang, Gyusam, Moon, Seokha, Nam, Giljoo, Kim, Chanyoung, Kim, Younghyun, Kim, Jinkyu, Kim, Sangpil
Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network. Moreover, objects in the overlap regio
Externí odkaz:
http://arxiv.org/abs/2207.00865
Autor:
Kim, Sungjune, Yun, Seongjun, Lee, Jongwuk, Chang, Gyusam, Roh, Wonseok, Sohn, Dae-Neung, Lee, Jung-Tae, Park, Hogun, Kim, Sangpil
Publikováno v:
In Information Sciences January 2024 653
