Search papers, labs, and topics across Lattice.
Southern University of Science and Technology
2
0
4
A novel source-anchored flow model achieves state-of-the-art video overlay removal, outperforming prior methods by over 70% on key perceptual metrics.
Forget incomplete video descriptions: a new dataset and training pipeline yields video captioning models that are competitive with Gemini-3-Pro while reducing hallucinations.