We implement our detector based on Faster R-CNN
In our implementation, the CNN model is fine-tuned from the VGG-16 on ImageNet.
3.5 GHZ ,1 Core
August 02, 2017 (1 year ago)
August 02, 2017 at 15:04:04 CET
Project page / code:
F. Yu, W. Li, Q. Li, Y. Liu, X. Shi, J. Yan. POI: Multiple Object Tracking with High Performance Detection and Appearance Feature. In BMTT, SenseTime Group Limited, 2016.
|0.89||3.5 GHZ ,1 Core|