Multiple action captioning

Sejong-VLI / V2T-Action-Graph-JKSUCIS-2023

The implementation of a paper entitled "Action Knowledge for Video Captioning with Graph Neural Networks" (JKSUCIS 2023).

MIT License

14 stars 3 forks source link

Multiple action captioning #3

Open rose-jinyang opened 12 months ago

rose-jinyang commented 12 months ago

Hello How are you? Thanks for contributing to this project. If there are 3 persons in a room and they is doing different independent actions each other, does this method extract such multiple independent action captions? And is it possible to localize the region (position) of acting object (person)?