DonaldKam
DonaldKam
That was great job. Can the **MotionNet** be separately trained with ground truth optical flow images？
As is illustrated in the paper, in training phase two affinity matrices are processd by row-wise or column-wise softmax. In test phase, how's the final affinity matrix computed since only...
Mentioned in the paper "We use multiples of three in the range [3,30] to form the grid, based on which δw = 12 and δb = 15 are selected in...
When run test_mot17.py cd python test_mot17.py The result is shown as follows. The title of each detected boxes represents (track id, detection id). However, it seems that in the results...
As there are more popular and high-efficient base networks, i.e. ResNetX, why select VGG as the feature extractor? As we know, it enjoys tremendous parameters that slow down the computation...
It will be awesome if the training scripts are also open so that we can validate its performance from scratch.
The authors say 'bottleneck' but why call that so? It seems the authors did not explain what 'bottleneck' refers to in the paper? Can you clarify?
Geometry-Guided Context Learning is a smart idea but it is difficult to find in the codes. Would you please localize it?
You stated that you adopted the Spatial configuration partitioning from STGCN in your paper. However, I could not find the correspondence in the codes. It will be appreciated if you...
What is the file **merge_joint_bone_data.py** used for?