Search papers, labs, and topics across Lattice.
3
0
4
Over 1,100 submissions reveal groundbreaking advancements in sports video understanding, with new methods pushing the boundaries of action prediction and localization.
The choice of pretraining strategy, not just model complexity, is the key driver of performance in fine-grained semantic segmentation tasks.
Distilling vision foundation models for segmentation doesn't have to sacrifice out-of-domain generalization: GKD achieves +10.6% gains over standard KD in foundation-to-local transfer.
