变化无常 发表于 2025-3-23 12:13:33

Toward Scale-Invariance and Position-Sensitive Region Proposal Networksaccuracy of an object detection method has been shown highly related to the average recall (AR) of the proposals. In this work, we propose an advanced object proposal network in favour of translation-invariance for objectness classification, translation-variance for bounding box regression, large ef

Additive 发表于 2025-3-23 16:09:58

http://reply.papertrans.cn/24/2342/234199/234199_12.png

真实的人 发表于 2025-3-23 18:50:27

http://reply.papertrans.cn/24/2342/234199/234199_13.png

visual-cortex 发表于 2025-3-23 23:48:52

http://reply.papertrans.cn/24/2342/234199/234199_14.png

美丽的写 发表于 2025-3-24 04:52:23

http://reply.papertrans.cn/24/2342/234199/234199_15.png

高原 发表于 2025-3-24 10:23:50

http://reply.papertrans.cn/24/2342/234199/234199_16.png

多样 发表于 2025-3-24 12:53:50

http://reply.papertrans.cn/24/2342/234199/234199_17.png

即席 发表于 2025-3-24 18:43:30

http://reply.papertrans.cn/24/2342/234199/234199_18.png

neoplasm 发表于 2025-3-24 21:41:46

http://reply.papertrans.cn/24/2342/234199/234199_19.png

attenuate 发表于 2025-3-25 00:05:31

http://reply.papertrans.cn/24/2342/234199/234199_20.png
页: 1 [2] 3 4 5 6 7
查看完整版本: Titlebook: Computer Vision – ECCV 2018; 15th European Confer Vittorio Ferrari,Martial Hebert,Yair Weiss Conference proceedings 2018 Springer Nature Sw