Ahmed Abdelkawy

Test blur_comp on video (236 frames)

2

I test your blur_comp on my image sequence (15 images) with resolution 1600 * 1200, and the results seem pretty good. However, I want to test on the whole video...

Please, Can you provide assignments without solutions for Specialization Deep Learning?

i was wandering if there is possibility to visualize Feature Maps in last Convolutional layer (before confidence maps for keypoints).

PoseConv3D pseudo heatmap volume

1

Thanks for your promising work (PoseConv3D). i am wandering about the reason of stacking pseudo heatmap of joints along temporal dimension instead single image containing all joints for example if...

PoseConv3D validation/test pipeline

1

Thanks for your great work. I have question regarding spatial size of pseudo heatmaps, in training pipeline, the size 58 X58 but in validation and test pipeline, the size of...

Calibration data

3

Dear Muhammad Haziq, First, your work is considered the main pillar in soccer analysis. but i need the calibration data along with their images to do camera calibration. can you...

Head pose estimation Only

1

Thanks for sharing your incredible work with us. Your algorithm runs at ~3 frames/sec on GPU. So, I am asking about getting the headpose prediction only using network architecture, is...

@ECHO960, Thanks for sharing such a valuable dataset to test the effectiveness of the multimodal action recognition models. After downloading the RGB_VIDEO folder from Google Drive, I found the following...