Abstract: Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions).
Abstract: Visual grounding focuses on localizing objects referred to by natural language queries. Existing fully and weakly supervised methods rely on a mass of language queries for training. However, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback