catalina17/VideoNavQA

An alternative EQA paradigm and informative benchmark + models (BMVC 2019, ViGIL 2019 spotlight)

⭐ 25 ⑂ 1 Python · 2022-06-22推送

https://arxiv.org/abs/1908.04950

benchmark deep-neural-networks machine-learning multimodal navigation question-answering video cross-modality vqa embodied visual-reasoning conditioning videonavqa

25

Watchers

0

贡献者

0

Commits

0

Releases

5

Open Issues

2022-06-22

最近推送

原文中文

暂无 README