yaruzz

Can not reproduce self-supervised packnet-sfm( training scratch) from on DDAD

2

Thanks for your great work! I'm quite interested in your excellent work. However, I have some questions. Firstly, I follow the `train_ddad.yaml` file,using 8 GPUs. But I can not reproduce...

Problem about trajectory association in target assign process of tracking module

1

Thanks for your excellent job, I have some questions regarding the generation of 'matched_tracklet' information. The process of matching track results to ground truth trajectories using the Hungarian algorithm (implemented...

Thanks for your impressive work! In the paper, Table 5 provides a comparison between using non-parametric queries and not. When using non-parametric queries, the box location is obtained by adding...

Thanks for your job. Making full use of large-scale unlabeled data is highly valuable and worth attention. I'm curious about the following: 1. why not use strong permutation augmentation when...