Summary of Beyond Uncertainty: Evidential Deep Learning For Robust Video Temporal Grounding, by Kaijing Ma et al.
Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding
by Kaijing Ma, Haojian Huang, Jin Chen, Haodong Chen, Pengliang Ji, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen, Xuelong Li
First submitted to arxiv on: 29 Aug 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 This paper presents a novel approach to improving Video Temporal Grounding (VTG) models by introducing SRAM, a robust network module that incorporates Deep Evidential Regression (DER) to quantify uncertainty during training. By estimating uncertainties based on user input, the model can address open-world challenges posed by open-vocabulary queries and untrimmed videos. The proposed Geom-regularizer enhances the uncertainty learning framework, making it more effective in VTG tasks. Experimental results demonstrate the effectiveness, robustness, and interpretability of SRAM and the uncertainty learning paradigm. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make video processing models better by adding a special tool called SRAM that uses Deep Evidential Regression to figure out when it’s unsure about something. This is important because current models are great at some things, but get confused with noisy or unusual data. The new module can say “I don’t know” in situations where it’s not sure what to do, which makes it more reliable and trustworthy. |
Keywords
* Artificial intelligence * Grounding * Regression
