3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
By combining FEMA-aligned annotations with high-resolution UAV imagery, the dataset establishes a standardized resource for developing and evaluating instance segmentation models that can support rapid post-disaster damage assessment and emergency response.
Persistent spatial anchors are essential for enabling shared and collaborative mixed reality (MR) experiences, but current anchor management mechanisms are typically centralized and lack transparent governance across multiple stakeholders. To this end, we explore a blockchain-based approach for governing spatial anchors in multi-user MR environments. We design and implement a decentralized anchor registry using a permissioned blockchain architecture that supports auditable anchor lifecycle management and cross-organization validation. A prototype system integrating a blockchain network, gateway services, and an MR client is developed to evaluate feasibility. Experimental results demonstrate that the proposed architecture can govern anchor lifecycle operations without degrading on-device rendering performance, while revealing a substantial gap between server-side and headset-experienced synchronization latency. We further analyze system performance from both server-side and device-side perspectives, highlighting the importance of client-experienced latency in MR deployments. The evaluation also shows that appropriate blockchain configuration can significantly reduce governance latency: tuning BatchTimeout from 2s to 500ms lowers latency by about 70% (from 5449ms to 1635ms) without affecting rendering performance on the MR device.
ClinX is introduced, an end-to-end multimodal PHI sanitization framework for medical image-text data, and results show that OCR-only masking is not sufficient as a standalone solution, and restoration-based sanitization better preserves clinically relevant visual context while sharply reducing recoverable PHI.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
