檢索結果：共6筆資料 檢索策略： "Transformer".ekeyword (精準) and cadvisor.raw="方文賢"
個人化服務 ：
排序：
每頁筆數：
已勾選0筆資料
1
Pose prediction found applications in a variety of areas. However, current methods adopting recurre…
2
In this thesis, two robust affine transformation-assisted methods with both real-world applications…
3
為了以深度學習方法實現先進駕駛輔助系統（ADAS），本論文提出了一種基於自我注意力機制的架構，此方法能夠偵測行車記錄器影片中的車禍發生時間。該方法首先透過 faster R-CNN 偵測並提取影片中…
4
This thesis presents an effective attention-based framework to detect accident in dashcam videos. I…
5
This thesis presents a new convolutional neural network (CNN)-based approach for first-person video…
6
Video context understanding has attracted increasing interests due to its potential applications in…