Closed grayfactory closed 1 year ago
This is not possible. Our model assumes a fully supervised setting, where action annotations (labels and onsets/offsets) are provided during training. Indeed, our work and prior works considers a subset of THUMOS14 dataset with temporal annotations. More details regarding the datasets and training schemes can be found in the paper.
Thank you for your quick reply. I get the point!
Hi, thanks for great work! I have question about to training model on dataset which without segment and label informations.
I expected that if the model could be trained by the THUMOS14 dataset, it would be equally possible to train with without annotations. but I found in meta_archs.py
Is it possible to train with data without label and segment information? Looking forward to your reply. Thank you.