SiamR-CNN icon indicating copy to clipboard operation
SiamR-CNN copied to clipboard

Siam R-CNN two-stage re-detector for visual object tracking

Results 10 SiamR-CNN issues
Sort by recently updated
recently updated
newest added

Hi! Coud you please provide the raw reasults of Lasot in 280 sequences?

Hi @pvoigtlaender, I was trying to reproduce your results on the VOT2018 but found significant differences between the reproduced and the reported scores. I was using the tensorpack model as...

Hi. Can you please guide me to integrate SiamRCNN with VOT-Toolkit?

Hi, How to run the tracker with my own video? I find the vot_2016 datasets are all pictures.Should I frame the video and give the groundtruth of first frame?

could you share me for pre-computeed the features date for hard example mining? my email is : [email protected] thank you !

Hello I just downloaded a traffic video from YouTube : https://www.youtube.com/watch?v=mrjqS5zd268&ab_channel=TaverNet I gave these values as ground truth : 258.0000,698.0000,388.0000,201.0000 When I run the tracker it starts great but as...

Hi, when I try to run python3 tracking/do_tracking.py --main main_otb2015, the following error will occurs. **`E tensorflow/core/common_runtime/executor.cc:642] Executor failed to create kernel. Invalid argument: Default MaxPoolingOp only supports NHWC on...

Does the current project support multi tracking or not ?, I tried giving multi ground truth in hope of multi track happening but no luck, if it doesn't support it...

Hello Thanks for the great job you guys did, I was wondering do you have any tips or ideas to improve the current accuracy?, where do you think it lacks...

Hello, I haven't been able to find this class ModelDesc in training