WonJun Moon

I am also very curious about this issue. It seems to be better than stage2

I also have the same problem with spacy 3.7.1 python 3.7.10

Thanks. I will wait for that. I still have problems here. It would be great if you give default parameter for the experiment in args!

@KevLuo I have tried to run the code with default parameters and following parameters. python collect_prediction.py 'TINY' 'TEST' 'TRUE' 128 1 1 'OSCRI_encoder' 32 '20closed_split0_closedval10_size32' './checkpoint/pat_30_div_TRUE_gap_TRUE_sched_patience_latsize_128_numrp_1_lambda_0.1_gamma_0.5_dataset_20closed_split0_closedval10_size32_01_64_32_OSCRI_encoder/' And results are as...

I ran the RPL official code for this split and the result is terrible, either. (Using 32x32 resolution) 63.0569111111111 | 61.4288777777778 | 64.7651666666667 | 60.7026888888889 | 62.0719888888889 AUROC for each...

We would also like to introduce 2 new papers regarding imbalanced learning. 1. Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition (AAAI 2023) [Arxiv](https://arxiv.org/abs/2211.13471) [GitHub](https://github.com/wjun0830/MOVE) [imbalance-MiniKinetics200 dataset](http://115.145.172.53:1215/AAAI_2023_MOVE_longtailed_minikinetics/index.html) This...

Hello. Thanks for your interest. I am not exactly sure since it was long ago. Maybe it was downloaded from [UMT](https://github.com/TencentARC/UMT?tab=readme-ov-file).

Does the error kessage comes out? If not, can you the performance? Other data when trained with cliplen 1 we remeber it worked fine

For now, the only thing I remember is that you may have to change the input parameters to PostProcessorDETR in inference.py! I am not sure if there are others to...

@awkrail Thank you!