search

dingfengshi / TriDet

[CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling
MIT License
160 stars 13 forks source link

on realistic videos #21

Open ailsa0506 opened 11 months ago

ailsa0506 commented 11 months ago

Hi, Thanks for your solid theoretical and experiment proof. I'd like to try to use your method for my own recorded videos and output the action categories and temporal positioning, what do you suggest for that! Looking forward to your reply.

dingfengshi commented 11 months ago

Hi, maybe you can try to extract the feature sequence for each video with a pretrained backbone and feed them into TriDet. If your dataset is small, you can try the same config with THUMOS14 first.