Search papers, labs, and topics across Lattice.
Beijing Institute of Technology
4
0
5
JFRDet achieves state-of-the-art performance in visible-infrared object detection by explicitly addressing severe geometric misalignment and illumination variability.
Frequency-domain fusion of RGB and event data significantly boosts object tracking performance, achieving a leading 76.6% precision on the challenging COESOT benchmark.
By dynamically adjusting state transitions based on event sparsity, MambaTrack achieves state-of-the-art RGB-Event object tracking, outperforming methods stuck with static transition matrices.
Fine-grained partitioning and targeted safeguards can provide robust NPU reliability with minimal performance overhead, challenging the assumption that redundancy is the only path forward.
