Summary of Enhancing Visible-infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning, by Ruiqi Wu et al.
Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning
by Ruiqi Wu, Bingliang Jiao, Wenxuan Wang, Meng Liu, Peng Wang
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Multimedia (cs.MM)
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 Visible-Infrared Person Re-identification (VI ReID) aims to match visible and infrared images of the same pedestrians across non-overlapped camera views. To address the challenge of modality-specific information, we introduce the Modality-aware and Instance-aware Visual Prompts (MIP) network built on the transformer architecture. The MIP model utilizes both invariant and specific information for identification by designing modality-specific prompts to reduce interference caused by the modality gap. Additionally, instance-specific prompts are employed to capture identity-level discriminative clues. Our proposed MIP outperforms most state-of-the-art methods on SYSU-MM01 and RegDB datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The VI ReID paper aims to match images of pedestrians taken from different cameras. It’s hard because the images can look very different depending on whether they’re in color or not. The authors created a new model that helps with this problem by using special prompts to focus on specific parts of the image. They tested their model on two big datasets and it did better than other similar models. |
Keywords
» Artificial intelligence » Transformer
