-
```
OSError: Unable to open file (unable to open file: name = 'data/VATEX/ordered_feature/SA/resnet152.pth/trn_ft.hdf5'
````
Could you tell me to use I3D feature?
-
Hi, cshizhe
I find that the number_of_feature/video_duration of videos are different, can you tell me the temporal interval of visual features?
Thanks
-
Hi,
Thanks for your great work. I have no problem using the code for MSVD-QA / MSRVTT-QA / the 3 other tasks of TGIF-QA, but as I train on TGIF-QA for FrameQA subtask, the loss quickly becomes nan…
-
非常感谢您开源代码，我仔细阅读了您的文章并重新复现了代码，收获很多。但是也存在一些疑问：
提取300个单词作为语义分支的训练标签，提取语义特征，该特征被映射到0-1之间。
问题1：语义特征和lstm的视觉输入、前一时刻的word-embedding,前一时刻的隐藏层h(t-1)分别对应相乘，达到语义融合的目的吗？
问题2：文章提到人工选取k个单词，那么选取的标准是什么呢？为什么选择300个，…
-
hello
the download link provided for msrvtt dataset: http:/www.robots.ox.ac.uk/~vgg/research/collaborative-experts/data/features/MSRVTT-experts.tar.gz is not available can you update the link? tha…
-
Hi Antoine, many thanks for sharing the code and data. Recently I would like to compare with your wonderfull model on your split test set. But I only obtained the sentence feature of test sentences, …
-
Thank you very much for your code! It has been very useful to me!
But, when I attempt to load the features in `msrvtt_resnext_eco.npy` file from the link that you included in the README, **ValueErro…
-
When I run `python train.py-c configs.train_stage1`, I find an error.
I only extracted the features of the `MSVD `dataset, and did not extract the `MSR-VTT` dataset. When I run `python train.py-c con…
-
While trying to replicate the results for msrvtt, the data loader for msvrtt requires the *"processing/raw-captions.pkl"* file which is not fetched as part of the features downloaded using the *"sync_…
-
Will also require `video.py`