1 code implementation • 1 Apr 2024 • Hyeongjun Kwon, Jinhyun Jang, Jin Kim, Kwonyoung Kim, Kwanghoon Sohn
Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details.
1 code implementation • 16 Mar 2023 • Tuan N. Tang, Kwonyoung Kim, Kwanghoon Sohn
To this end, we introduce TemporalMaxer, which minimizes long-term temporal context modeling while maximizing information from the extracted video clip features with a basic, parameter-free, and local region operating max-pooling block.
Ranked #1 on Temporal Action Localization on MUSES
1 code implementation • 8 Nov 2022 • Tuan N. Tang, Jungin Park, Kwonyoung Kim, Kwanghoon Sohn
In addition, the evaluation for Online Detection of Action Start (ODAS) demonstrates the effectiveness and robustness of our method in the online setting.
1 code implementation • 27 Jul 2022 • Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, Kwanghoon Sohn
To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation.