search

hyounghk / VideoQADenseCapFrameGate-ACL2020

Code for ACL 2020 paper "Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA." Hyounghun Kim, Zineng Tang, Mohit Bansal.
MIT License
34 stars 10 forks source link

Textual features #5

Open engindeniz opened 3 years ago

engindeniz commented 3 years ago

Could you share your code for textual feature extraction steps or give more detail on it (e.g Roberta and GloVe features), please?

hyounghk commented 3 years ago

Sorry for late response. You can refer to this repository for extracting GloVe feature: https://github.com/hengyuan-hu/bottom-up-attention-vqa/blob/392520640e3d9aed0009ddfe207901757b10b9a6/tools/create_dictionary.py#L27

For Roberta, the code that I used is not clean. But, if you still need it, please let me know. I can share the code block via email.

engindeniz commented 3 years ago

Hi,

Thank you for your reply. If you can share the code block, it would be nice.