Weakly-Supervised Temporal Localization via Occurrence Count Learning

(Accpted at ICML 2019)

Only codes for the MAPS experiment are submitted as other codes are almost identical

The weakly supervised model with additional methods:

• WeaklyNetworkModel.py

The main script that runs the training

• main.py

The dataset creation

• new_createDataset.py
• google_create_dataset.py

File for inference

• infer.py
• final_score.py

Configuration file:

• config.py

In addition, subfolder contain all utility functions used throughout the project.

Please feel free to contact me directly if you have any question. Personal Page