Constrained video face clustering using 1NN relations
In this work, we introduce the Constrained first nearest neighbour Clustering (C1C) method for video face clustering. Using the premise that the first nearest neighbour (1NN) of an instance is sufficient to discover large chains and groupings, C1C builds upon the hierarchical clustering method FINCH...
Huvudupphovsmän: | Kalogeiton, V, Zisserman, A |
---|---|
Materialtyp: | Conference item |
Språk: | English |
Publicerad: |
2020
|
Liknande verk
-
Face, body, voice: video person-clustering with multiple modalities
av: Brown, A, et al.
Publicerad: (2021) -
LAEO-Net++: revisiting people looking at each other in videos
av: Marin-Jimenez, MJ, et al.
Publicerad: (2020) -
LAEO-Net: Revisiting people looking at each other in videos
av: Marin-Jimenez, M, et al.
Publicerad: (2020) -
Smooth-AP: Smoothing the path towards large-scale image retrieval
av: Brown, A, et al.
Publicerad: (2020) -
Automated video labelling: identifying faces by corroborative evidence
av: Brown, A, et al.
Publicerad: (2021)