The 2nd International StepUP Competition for Biometric Footstep Recognition focused on advancing pressure-based footstep biometrics. This year's competition introduced challenges in generalizing to unseen users with limited data, maintaining robustness to domain shifts from footwear and speed variations, and effectively fusing left-right footsteps. The ArogyaPandit Research Team achieved the best equal error rate of 8.00% using a spatiotemporal CNN, though recognizing users with unseen footwear remains difficult. AI
IMPACT Advances research in biometric identification through novel CNN architectures and data fusion techniques.
RANK_REASON The cluster describes a research competition and its results, including a published paper.
- alphaXiv
- ArogyaPandit Research Team
- arXiv
- CatalyzeX
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- ScienceCast
- spatiotemporal CNN
- StepUP Competition Series
- StepUP-P150 dataset
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
