TheShadow29 / VidSitu

[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)

https://vidsitu.org/

TheShadow29/VidSitu Issues

About the 'vb_lst' for vinfo_files for validation
Closed 3 months ago2
Running feature extraction on own videos.
Updated 4 months ago3
Not able to download all the videos
Updated 5 months ago3
Question about reproduce SlowFast+NL verb model
Updated a year ago1
The evaluation code is inconsistent with the README file description
Closed a year ago2
I have downloaded situ_vidfeats_drive and vsitu_vocab, do I need to download the video?
Updated a year ago9
Why testset annotations for SRL and EventRelation task released?
Closed 2 years ago2
All pkl files in vsitu_vocab directory
Updated 2 years ago9
What is the version of yt-dlp?
Closed 2 years ago7
Not able to download the full dataset
Closed 3 years ago6
Modified Data Prep Instructions
Closed 3 years ago1
Regarding the SlowFast NL verb prediction run
Closed 3 years ago2
Assertion Error cfg.mdl.mdl_name == "sf_base" when running main_dist.py
Updated 3 years ago7
Add Feature Extraction code for Semantic Role Prediction and Event Relation.
Closed 3 years ago
Clarify Docs for Running Pre-Trained Models
Updated 3 years ago
Pretrained Model Checkpoint
Closed 3 years ago2
hi~ about gpu and others
Closed 3 years ago2
Download Age-Restricted Videos
Closed 3 years ago
Verbs missing?
Updated 3 years ago1
Problem on the downloading videos
Closed 3 years ago3
Issue in downloading video and extracting frames
Closed 3 years ago9