Factorized Graph Matching is proposed for
better optimizing and understanding graph matching
Canonical Time Warping is proposed for
temporally aligning multi-modal sequences.
Aligned Cluster Analysis is proposed to
temporally cluster human behavior.
An Unsupervised System is proposed to
discover facial events from video of naturally occurring facial
Exemplar-based Graph Matching is proposed to
robustly localize facial landmarks on image.
Time Mapping generates low-frame-rate video
from a high-frame-rate input using Video
Spatio-temporal Matching is proposed for
detecting and tracking humans in videos.
Bipartite-Graph Labels is proposed to
exploit the rich relationships among fine-grained object
MagFace learns a universal feature embedding
whose magnitude can measure the quality of the given face.