-
Hi, thanks for your awesome work! I recently run the public naive SFT and CIL 512 checkpoint following the B.3 Evaluation setting and get the following result, which may be different from paper report…
-
In the paper, an image-net pretrained resnet18 model can achieve a score of 77.2 with only RGB modality. However, there is no code for UCF101 in the repo. I tried to train a resnet18 according to the …
-
I have downloaded your pre-computed RGB images, but I have some problems in merging the three parts (ucf101_jpegs_256.zip.001, ucf101_jpegs_256.zip.002, ucf101_jpegs_256.zip.003) into one .zip file. I…
-
感谢您们优秀的工作，我想知道在Table 4中，在ucf101以及hmdb51数据集迁移的结果，是在k400上预训练800epoch还是1600epochs的权重？
-
I apologize for bothering you again. Recently, I have been working on customizing a dataset similar to UCF101-24. Do you have any good suggestions, such as annotation tools, etc.? During my search, I …
-
After download the dataset and run 'cat ucf101_jpegs_256.zip* > ucf101_jpegs_256.zip', I try to unzip the file, use the command 'unzip ucf101_jpegs_256.zip', but a problem occured, 'jpegs_256/v_Trampo…
-
Thank you for sharing your work on the Zigzag Mamba Diffusion Model. The paper mentions video generation experiments on the UCF101 dataset, but I noticed that the video generation results and checkpoi…
-
Hi, does the UCF101 dataset not require any processing? Only CSV files need to be divided and then used as input? That means the video input format is the original avi format?Looking forward to your r…
-
-
Thanks for sharing your code. I use your code to train on UCF101 with the suggested hyper-parameters (i.e., lr=0.001, trans_linear_out_dim=1152， img_size=224, tasks_per_batch =16, num_test_tasks=1000…