Tracking Persons-of-Interest via Unsupervised Representation Adaptation

Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically
different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up. Existing multi-target tracking methods often use low-level features which are not sufficiently discriminative for identifying faces with such large appearance variations.

Read More “Tracking Persons-of-Interest via Unsupervised Representation Adaptation”

Unsupervised 3D Pose Estimation for Hierarchical Dance Video

Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre). We propose a Hierarchical Dance Video Recognition framework (HDVR). HDVR estimates 2D pose sequences, tracks dancers, and then simultaneously estimates corresponding 3D poses and 3D-to-2D imaging parameters, without requiring ground truth for 3D poses.

Read More “Unsupervised 3D Pose Estimation for Hierarchical Dance Video”