Hello，I am preparing an ECCV paper about natural language guided video retrieval in a single. I want to compare the results of mine with your model on ActivityNet Caption and Charades-STA datasets. Can you offer me the details of your experiments,such as the parameters of clip? [I have modified your codes for ActivityNet Caption and Charades-STA datasets ].(https://github.com/YangYangGirl/TALL.pytorch/blob/280fcb07f55c1676248423a382f6a2f68c52c98e/dataset.py#L644)
Hello，I am preparing an ECCV paper about natural language guided video retrieval in a single. I want to compare the results of mine with your model on ActivityNet Caption and Charades-STA datasets. Can you offer me the details of your experiments,such as the parameters of clip? [I have modified your codes for ActivityNet Caption and Charades-STA datasets ].(https://github.com/YangYangGirl/TALL.pytorch/blob/280fcb07f55c1676248423a382f6a2f68c52c98e/dataset.py#L644)
Sincerely need your help.Thank you!