no code implementations • NeurIPS 2021 • Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, Chuang Gan
This paper introduces a new benchmark that evaluates the situated reasoning ability via situation abstraction and logic-grounded question answering for real-world videos, called Situated Reasoning in Real-World Videos (STAR Benchmark).
1 code implementation • 1 May 2023 • Benjamin Lipkin, Lionel Wong, Gabriel Grand, Joshua B Tenenbaum
These results inform the inferential capacity of statistical language models, and their use in pragmatic and semantic parsing applications.