Search Results for author:
Found 5 papers, 3 papers with code
Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
Recent works in implicit representations, such as Neural Radiance Fields (NeRF), have advanced the generation of realistic and animatable head avatars from video sequences.
DC-Former: Diverse and Compact Transformer for Person Re-Identification
In this paper, we propose a Diverse and Compact Transformer (DC-Former) that can achieve a similar effect by splitting embedding space into multiple diverse and compact subspaces.
HBReID: Harder Batch for Re-identification
Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away.
A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual News Anchors
Lip sync has emerged as a promising technique for generating mouth movements from audio signals.
Constrained Lip-synchronization
Image-to-Image Translation
+1
Joint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification
RBRL inherits the ranking loss minimization advantages of Rank-SVM, and thus overcomes the disadvantages of BR suffering the class-imbalance issue and ignoring the label correlations.
