Factorized Graph Matching is proposed for better optimizing and understanding graph matching problems.

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 behavior.

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 Saliency.

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 classes.

MagFace learns a universal feature embedding whose magnitude can measure the quality of the given face.