Search papers, labs, and topics across Lattice.
DTrack) [22, 9]. ***Code and trained models will be made publicly available upon acceptance.
2
0
4
Event-based vision gets a lightweight, efficient boost: E-TIDE matches state-of-the-art forecasting accuracy while slashing model size and training costs.
SNNs can now learn robust visual representations from unlabeled event data, rivaling supervised learning in low-data regimes, thanks to a new contrastive self-supervised learning framework.
