Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions
Wenxuan Wang, Yisi Zhang, Xingjian He, Yichen Yan, Zijia Zhao, Xinlong Wang, Jing Liu
Welcome to this repository for the latest updates.
โ [2024.2.17] : Released our paper on arXiv.
โ [2024.5.16] : Our paper is officially accepted by ACL 2024.
[ ] : Released our data and baselines.
In this work, we take a step further to the intention-driven visual-language (V-L) understanding. To promote classic VG towards human intention interpretation, we propose a new intention-driven visual grounding (IVG) task and build a largest-scale IVG dataset named IntentionVG with free-form intention expressions. Considering that practical agents need to move and find specific targets among various scenarios to realize the grounding task, our IVG task and IntentionVG dataset have taken the crucial properties of both multi-scenario perception and egocentric view into consideration. Besides, various types of models are set up as the baselines to realize our IVG task. Extensive experiments on our IntentionVG dataset and baselines demonstrate the necessity and efficacy of our method for the V-L field. To foster future research in this direction, our newly built dataset and baselines will be publicly available.
If you use our data or baseline model in your work or find it is helpful, please cite the corresponding paper:
@article{wang2024beyond,
title={Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions},
author={Wang, Wenxuan and Zhang, Yisi and He, Xingjian and Yan, Yichen and Zhao, Zijia and Wang, Xinlong and Liu, Jing},
journal={arXiv preprint arXiv:2402.11265},
year={2024}
}
This work is built on many excellent research works and open-source projects, thanks a lot to all the authors for sharing!
1.EVA-CLIP
2.Qwen-VL