Search Results for author:
Found 2 papers, 0 papers with code
Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment
Human face reenactment aims at transferring motion patterns from one face (from a source-domain video) to an-other (in the target domain with the identity of interest). While recent works report impressive results, they are notable to handle multiple identities in a unified model.
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
