HQGA

HQGA copied to clipboard

Hi, I wanna know how to set specific frames per second?

4

In your paper, you said extracted each video in MSVD-QA p=15 frames per second. I found in HCRN that they use all frames. I hope you can tell how to...

LemonQC

Thank you for your excellent work! Should I extract image from raw video before I extract feature by BUTD？ Should I save the pre-proposed bbox and output feature in the...

dongfengxijian

About the BERT feature

1

It was a excellent work and I have learned a lot in this work. But I am still confused about the extraction of BERT, I can't extract it and reappear...

c1393428962

Features of MSRVTT-QA

1

Thank you for sharing such great work! I am very interested in it! But I have many difficulties in MSRVTT feature extraction, and my GPU is relatively poor. Therefore, I...

songbo125

Hi, can you pleaese release the pre-extracted TGIF feature?

1

much appreciated!

qyx1121

vacuum-cup

About the box region feature for NExT-QA

1

Thanks for your code! How can I obtain the extracted bbox region features for NExT-QA? Looking forward to your reply.

zhangxi1997

how much GPU memory does the next QA need?

6

vacuum-cup

Visualization

3

Hi, Very interesting work I wanted to know if there was a way to produce the graphs given a video like shown in the README Thank you

estelleafl

answer set for NExT-QA？

2

Hi, thanks for your sharing. I didn't find ans_word.json file in nextqa folder. How many answers of high frequency are used as predefined answer set for NExT-QA ? How do...

wu-shuqi