OpenTAD
OpenTAD copied to clipboard
sming256
OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.
We keep this issue open to collect feature requests and feedback from users, and thus keep improving this codebase. If you didn't find the features you need in the [Road...
Does the Apache License apply to all models in the repo, and specifically does it apply to the Adatad model? Thanks!!
Thank you for your outstanding work! How to train adapters in TAD models outside the backbone network
Hello! Thanks for putting together this toolbox. I have a private dataset of continuous videos (up to about 30m in length) comprising about a half dozen different skills that I...
Hi, I have tried to train a AdaTAD model on [IKEA ASM](https://github.com/IkeaASM/ikea_asm_dataset) dataset. I followed the THUMOS config using VideoMAE base model. The final epoch output is: ``` 2024-07-15 09:17:18...
Hello! First of all, thank you for your constructive work on video action detection. Now, based on my own data, I've trained an adaTAD model with your framework, but I...
Thanks for the great work! I wonder how to use exsiting tools to measure FLOPs efficiency of the model?
Hello, Thanks for the great work. I would like to run action localization on some custom egocentric videos. Is there a demo code that I can use? If the code...
Hi @sming256 🤗 I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to...
Hello Author！ Why Thumos 14 in paper form dataset and the Activity net dataset show the accuracy of the precision and _https://github.com/sming256/OpenTAD/tree/main/configs/adatad_ is not the same? For example: in https://github.com/sming256/OpenTAD/tree/main/configs/adatad:...
