A wavelet attention fusion and YOLO based approach for robust multi scale hand pose estimation
Bhavana Sharma, Jeebananda Panda · 2026
Read A wavelet attention fusion and YOLO based approach for robust multi scale hand pose estimation by Bhavana Sharma, Jeebananda Panda (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13408687.txt.
Description
Bhavana Sharma and Jeebananda Panda present a method to estimate three-dimensional hand pose across multiple scales. Their 2026 paper deals with a hard vision task: joints bend in complex ways, hands are partly hidden, and appearance varies by person.
Their framework joins a wavelet attention fusion module with a modified YOLOv11 detector. Wavelet decomposition keeps high-frequency edge detail while boosting low-frequency semantic features, which helps rebuild fine joint positions. Detection outputs feed a multi-scale backbone with an EfficientNet spatial extractor and gated recurrent units for time order. The design aims at real-time, robust pose tracking in real-world multi-view data.
Catalog record
| CREATOR | Bhavana Sharma, Jeebananda Panda |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |