Skip to Main content Skip to Navigation
New interface
Conference papers

Video Face Clustering with Unknown Number of Clusters

Abstract : 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 based on their identity. Different from previous work in this area, we choose to operate in a realistic and difficult setting where: (i) the number of characters is not known a priori; and (ii) face tracks belonging to minor or background characters are not discarded. To this end, we propose Ball Cluster Learning (BCL), a supervised approach to carve the embedding space into balls of equal size, one for each cluster. The learned ball radius is easily translated to a stopping criterion for iterative merging algorithms. This gives BCL the ability to estimate the number of clusters as well as their assignment, achieving promising results on commonly used datasets. We also present a thorough discussion of how existing metric learning literature can be adapted for this task.
Document type :
Conference papers
Complete list of metadata
Contributor : Makarand Tapaswi Connect in order to contact the contributor
Submitted on : Friday, January 10, 2020 - 5:50:43 PM
Last modification on : Friday, November 18, 2022 - 9:24:51 AM

Links full text


  • HAL Id : hal-02435407, version 1
  • ARXIV : 1908.03381



Makarand Tapaswi, Marc T. Law, Sanja Fidler. Video Face Clustering with Unknown Number of Clusters. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. ⟨hal-02435407⟩



Record views