Jie Lei 雷杰
Jie Lei 雷杰
Hi @hpppppp8, I don't have raw videos to share right now. But since all the videos are on YouTube, you should be able to download it with tools such as...
Thanks for the great repo! Do you have plans adding S3D and S3D-G from https://arxiv.org/abs/1712.04851? They achieve better performance than the I3D model while runs much faster. Here is a...
谢谢提醒！
I am working on it, hoping to bring it back on readthedocs.org, sorry for the inconvenience.
Hi @skotey, We have provided the extracted audio files along with the video frames, you can fill out this [form](https://docs.google.com/forms/d/e/1FAIpQLSftzvAtUSnsmuwpKk5PU9bS7lk4FOu_v9Y2vq2nGjRXKoh6tw/viewform) to download them. -- Jie
@chahna107 given only desired image height/width, calculate the image width/height based on the original image aspect ratio. Simply replace ``` options.width || (options.width = image_element.width); options.height || (options.height = image_element.height);...
Hi @bjuncek, `located frame` are generated based on the original timestamps from annotators, as sometimes our extract clips appear longer than they really are (may be caused by some ffmpeg...
Sorry, not sure why this happens, I've never run into this issue.
Thanks for letting me know! Our web server is down due to a hardware failure, we are working on a fix but we don't have an ETA yet. I'll keep...
The data is now back in [this new link](https://nlp.cs.unc.edu/data/jielei/tvqa/tvqa_public_html/). Best, Jie