Summary of Apollo: An Exploration Of Video Understanding in Large Multimodal Models, by Orr Zohar et al.
Apollo: An Exploration of Video Understanding in Large Multimodal Models
by Orr Zohar, Xiaohan Wang, Yann Dubois, Nikhil Mehta, Tong Xiao, Philippe Hansen-Estruch, Licheng Yu, Xiaofang Wang, Felix Juefei-Xu, Ning Zhang, Serena Yeung-Levy, Xide Xia
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 The paper investigates the mechanisms driving video understanding in Large Multimodal Models (LMMs), which are increasingly integrated into various applications. Despite their widespread adoption, the underlying processes remain poorly understood, leading to design decisions lacking justification or analysis. The authors’ comprehensive study aims to uncover what effectively drives video understanding in LMMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how Large Multimodal Models (LMMs) understand videos. Right now, we don’t fully know why they work the way they do, so it’s hard to make good decisions about designing these models. The authors want to figure out what makes them good at understanding videos. |
