Search papers, labs, and topics across Lattice.
Ho Chi Minh City University of Technology
2
0
5
Achieving a staggering 95.41% mAP@10, FaLCon revolutionizes text-based person anomaly search by combining global semantic matching with fine-grained verification to tackle the Sim2Real challenge.
Semantic-F1 not only outperforms traditional metrics but also reveals critical insights into the reliability of automated fact-checking systems.
