Search papers, labs, and topics across Lattice.
National 111 Project Base of Intelligent Information Processing
2
0
5
Achieving a top rank in the MeViS-Audio challenge, this system showcases the power of agreement-based segmentation in accurately identifying objects described by spoken expressions.
Current video generation benchmarks overlook crucial aspects of physical plausibility and temporal coherence, highlighting the need for holistic evaluation metrics like PhyScore.
