Closed zzg-zzg closed 3 years ago
@zzg-zzg Thank you for your kind reminder.
Q: whether dividing the features extracted by keys and values will affect the detection of occluded objects? A: no.
Q: What should I do if I want the bbox to contain the occluded part? A: Frankly speaking, it's not easy to get the bounding boxes that contain the occluded parts. A straightforward solution is to using the historical target information, especially the one in the previous frame.
This issue is closed. Feel free to create new issues if you have any questions.
Thank you for your excellent work. I read your paper and found an obvious typo. In the last paragraph of section 3.3 ,STM's citation number should be [37] and GraghMemVOS should be [30]. Another question I want to know is whether dividing the features extracted by keys and values will affect the detection of occluded objects. What should I do if I want the bbox to contain the occluded part?