search

TencentARC / MCQ

Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).
136 stars 16 forks source link

How to finetune on the MSRVTT #6

Open ForawardStar opened 2 years ago

ForawardStar commented 2 years ago

Hello, wonderful project!. Here I wonder how to finetune the pre-trained models on downstream video-text retrieval datasets like MSR-VTT, LSMDC, and MSVD? I notice that the script for zero-shot retrieval has been provided, but there is no script about how to finetune on retrieval datasets.

hayyubi commented 2 years ago

I am planning to use the model as a baseline for my model. Will be great if the authors could point/release the code for finetuning.