Search papers, labs, and topics across Lattice.
4
0
3
FASR++ transforms low-quality surveillance images into high-resolution facial representations, achieving state-of-the-art recognition accuracy without compromising identity integrity.
Visibility analysis in Dota 2 reveals behavioral patterns that structured data alone can't uncover, challenging existing analytics paradigms in MOBA research.
Self-supervised learning can achieve over 97% accuracy in parking spot occupancy recognition without requiring labeled data from the target environment.
Achieving a macro accuracy of 79.7% in vehicle color recognition highlights the potential of synthetic data augmentation to address severe class imbalances in surveillance contexts.
