-
thanks for your great work!
i use the checkpoint in [https://huggingface.co/wangyueqian/HawkEye/tree/main](url) to test grounding performance, but the results i get have a large margin compare with t…
-
Hi,
How to create a new dataset just like the format of "ActivityNet Captions" with my own video? THX!
-
This is a very meaningful job, but I would like to ask how to obtain the video data for the Charades-Sta and ActivityNet Captions videos?
-
# ActivityNet Large Scale Activity Recognition Challenge 2017 #
- Author: Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, T…
-
Hello, thank you for sharing and looking forward to the code! I was wondering whether you will be planning to release the generated captions from your model? I'm particularly interested in the ones fo…
-
I followed the instructions in [README](https://github.com/google-research/scenic/tree/main/scenic/projects/vid2seq#training) to evaluate the released checkpoints, but I could not reproduce the result…
-
Thank you for your excellent work. I want to run your model on my own data set, but you are training based on extracted features, can you disclose how to extract C3D video features from the data set? …
-
Please reply to this issue if you met any problem downloading the videos ;)
**Fill the form** (https://forms.gle/aMywVrNxAvXffm9H7) _seriously_ to download the videos from Google Drive or Baidu Yun…
-
I am doing violence detection using video captioning. If I give your model a number of videos containing some type of violence will it be able to tell that in captions?. Example if a tree is on fire i…
-
The denifition of axes in the paper is "The left density plots in Fig. 3 show the overall distributions of the temporal moment locations in Charades-STA and ActivityNet Captions, where the horizontal…