We present a new clustering method in the form of a single clustering equation that is able to
directly discover grou**s in the data. The main proposition is that the first neighbor of each …

Given a large collection of unlabeled face images, we address the problem of clustering
faces into an unknown number of identities. This problem is of interest in social media, law …

Understanding videos such as TV series and movies requires analyzing who the characters
are and what they are doing. We address the challenging problem of clustering face tracks …

Historically, the principal interest in the typed λ-calculus is in connection with Godel's
functional (" Dialectica") interpretation'of intuitionistic arithmetic. However, since the early …

A good clustering algorithm can discover natural grou**s in data. These grou**s, if used
wisely, provide a form of weak supervision for learning representations. In this work, we …

The objective of this work is person-clustering in videos--grou** characters according to
their identity. Previous methods focus on the narrower task of face-clustering, and for the …

Analyzing the story behind TV series and movies often requires understanding who the
characters are and what they are doing. With improving deep face models, this may seem …

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 …

We present an end-to-end system for detecting and clustering faces by identity in full-length
movies. Unlike works that start with a predefined set of detected faces, we consider the end …

Clustering faces in movies or videos is extremely challenging since characters' appearance
can vary drastically under different scenes. In addition, the various cinematic styles make it …