Summary of Star: a Benchmark For Situated Reasoning in Real-world Videos, by Bo Wu and Shoubin Yu and Zhenfang Chen and Joshua B Tenenbaum and Chuang Gan
STAR: A Benchmark for Situated Reasoning in Real-World Videos
by Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, Chuang Gan
First submitted to arxiv on: 15 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces the Situated Reasoning in Real-World Videos (STAR Benchmark) for evaluating machine intelligence’s ability to reason in real-world situations. The benchmark uses real-world videos with human actions or interactions, which are dynamic, compositional, and logical. It assesses situated reasoning via situation abstraction and logic-grounded question answering. The dataset includes four types of questions: interaction, sequence, prediction, and feasibility. Existing video reasoning models struggle on this task, highlighting the need for a diagnostic neuro-symbolic model that can disentangle visual perception, situation abstraction, language understanding, and functional reasoning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes a new benchmark to test if computers can think about real-life situations. It uses videos of people doing things and asks questions about what’s happening in the video. The computer has to understand the situation and answer the question correctly. This is hard because the videos are complex and have lots of things happening at once. The paper shows that current computer models aren’t good at this task, so they need a new way to think about situations. |
Keywords
» Artificial intelligence » Language understanding » Question answering
