Search papers, labs, and topics across Lattice.
2
0
2
0
Efficient Unified Multimodal Understanding (EUMU), the winning solution for the MUMU Track of the 8th LSVOS Challenge, builds on a shared pretrained multimodal model, using its prompt-based capabilities for detection and captioning and training lightweight heads on shared visual features to predict quality, scene, and event tags.
WiFi-JEPA outperforms traditional methods by leveraging self-supervised learning to create robust 3D human pose estimations from WiFi signals, even in challenging environments.
