Ruopeng Gao
Ruopeng Gao
这个我也没有他们的直接联系方式，你可以尝试通过官方途径联系他们，我之前用的是邮箱：[email protected]
Thanks for your thumbs up. This is a pretty interesting question, and I will try to explain my thoughts as briefly as I can. The phenomenon you observed is because...
I'm sorry for the delay in my responses. I'll be in the hospital for a while (maybe a month or more), so my replies might be slower than usual. Thanks...
Thank you all for the thoughtful and proactive discussions. I believe that handling infinite-length occlusions is an engineering problem that requires some additional implementations or modules. If you can introduce...
I'm sorry that the code you provided wasn't well formatted. Did you use the demo code we provide?
Are you using your custom dataset or the dataset included in our repository?
> my custom dataset, the video for demo is from the dataset Apologies for missing your previous message. Have you resolved this discrepancy between the demo result and evaluation metrics?...
As you said: > I run the demo code, found many objects were not detected in output videos, while the evaulation metrics are reasonable. It's wired because I think you...
> When I used two videos, one is from dataset, another is out of dataset, while objects in both videos are fruit fly/drosophila ... former video results is better than...
I have closed this issue due to a long period of inactivity.