-
Hi, Arka. Thanks for your work.
I am interested in using this dataset for temporal grounding. However, I think I get some misconceptions about the annotations of gt_frms. I am wondering how should I …
-
Hello,
Thank you for responding to all issues. I have one question.
I inferenced my own video, but sentences accuracy is not so good.
So, I want to append more captions in dataset -> and trai…
-
EPOCH [Valid] 76 epoch 28424 iter, R1-0.1 = 0.7490, R1-0.3 = 0.5767, R1-0.5 = 0.3995, R1-0.7 = 0.2183, mIoU = 0.4008
2020-09-09 20:13:50 ITER Step 28500 grounding = 0.0022, tag = 3.1444, dqa = 0.0850…
-
Hi,
Thank you for your work. I'm making code to allow for easy testing of caption generation on user videos. Can you tell me how I can generate captions for my own videos?
What features are re…
-
Hi Vladimir,
Noticed in the MDVC codebase that you load the I3D CONV features from "./data/sub_activitynet_v1-3.i3d_25fps_stack24step24_2stream.hdf5"
Some questions:
(i) Do you have a script th…
-
Hi, thank you a lot for the excellent work!
I am trying to download all preprocessed features while I didn't find the preprocessed features for ActivityNet-Caption following the box link you provi…
-
I have a error, when run:python prepare_activitynet.py
FileNotFoundError: [Errno 2] No such file or directory: 'data/activitynet/captions/train.json
where I can download: train.json/val_1.json/val_…
-
Thanks for your released code!
I am new to "text-video retrieval" task, and wonder why the retrieval result of ClipBERT is much lower than that in paper "Support-set bottlenecks for video-text rep…
-
Hi,
I am trying to run the single_prediction.py for a different video with pretrained BMT model. It requires i3d features as well. The features that are uploaded are giving the corrupted error. Could…
-
Hi, as #9 said, I could download extracted features of activitynet. But I want know how to use the file `pac_activitynet_v1-3.hdf5` beacuse I want use this dataset with Charades-STA's model. Thank you…