Open chenqz1998 opened 2 years ago
Hi,
Training without the background dataset may cause a significant drop in performance. As stated on the website of VCDB, please drop a mail to the authors for the background dataset.
Thanks for your reply. I have dropped a mail to the VCDB authors but received no replies. Could you please share the extracted features of VCDB and FIVR-5K to facilitate reproducibility for this research? Many thanks again.
The background dataset is very large (~1.1TB). I have to use the core dataset without background dataset to train the model. How can I modify the annotation file (vcdb.pickle)?