TheShadow29/VidSitu
[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)
PythonMIT
Issues
- 4
Question about reproduce SlowFast+NL verb model
#24 opened by wkw1259 - 2
- 3
Running feature extraction on own videos.
#25 opened by Andrew-Zhang - 3
Not able to download all the videos
#26 opened by debadityaroy - 2
- 9
I have downloaded situ_vidfeats_drive and vsitu_vocab, do I need to download the video?
#20 opened by ttx213 - 2
- 9
All pkl files in vsitu_vocab directory
#4 opened by cws7777 - 7
What is the version of yt-dlp?
#21 opened by a670531899 - 6
Not able to download the full dataset
#7 opened by rui1996 - 1
Modified Data Prep Instructions
#19 opened by dfan - 2
Regarding the SlowFast NL verb prediction run
#18 opened by fanyix - 7
- 0
Add Feature Extraction code for Semantic Role Prediction and Event Relation.
#14 opened by TheShadow29 - 0
Clarify Docs for Running Pre-Trained Models
#13 opened by TheShadow29 - 2
Pretrained Model Checkpoint
#11 opened by yrf1 - 2
hi~ about gpu and others
#10 opened by jun0wanan - 0
Download Age-Restricted Videos
#8 opened by TheShadow29 - 1
Verbs missing?
#6 opened by brandonclark314 - 3
Problem on the downloading videos
#5 opened by liujiaheng - 9