Chen Gao
Chen Gao
Yes, it depends on the resolution as well because we need to feed the whole video to the memory. What is the resolution?
压缩包里面并没有结果视频. 请提供flow, edge, 以及最终补全的视频. 另外, 您提供的视频是sample use only. 这可能涉及到copyright的问题.
You can find all the files at https://drive.google.com/drive/u/2/folders/1aIYkkltzelHyh05RYve0AQW2dCe8SL2W Let me know if you have other question.
Thanks for the question. We follow the processing steps by prior work (Visual Semantic Role Labeling, Detecting and Recognizing Human-Object Interactions) to remove prediction scores for certain action-object pairs. You...
As I recall, we will lose around 3mAP without post-processing. The mAP should be around 42. I will check and see where is the problem.
1. When you say "the scene changes greatly", do you mean the camera motion is large, or the objects in the scene have a large motion? Camera motion: if the...
Hi @Edward334, thanks for this detailed report! Yes, the image inpainting network requires that the height and weight should be divided by 8. One trivial solution is to resize the...
Hi @Carbord, Sorry for the confusion. The parameter "--Demo_RCNN demo/Object_Detection.pkl" is just for specifying the path to store the output result. You can simply run step3 and 4. These two...
@zhaowuyao, there are five steps listed in the **Demo/Test on your own images** section. Step 1 is for setting up the external object detector. Then please put your own images...
Hi @vaesl, I am working on the iCAN v2. Once finished, I will update the visualization code which will support HICO-DET as well.