TY - JOUR
T1 - A Coupled Hidden Markov Random Field Model for Simultaneous Face Clustering and Tracking in Videos
AU - Wu, Baoyuan
AU - Hu, Bao-Gang
AU - Ji, Qiang
N1 - KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: The work was completed when the first author was a visiting student at Rensselaer Polytechnic Institute (RPI), supported by a scholarship from China Scholarship Council (CSC). We thank CSC and RPI for their supports. Qiang Ji is supported in part by a grant from the US National Science Foundation (NSF, No. 1145152). Bao-Gang Hu and Baoyuan Wu are supported in part by the National Natural Science Foundation of China (NSFC, No. 61273196 and 61573348). We greatly thank Professor Siwei Lyu for his constructive comments to this work.
PY - 2016/10/26
Y1 - 2016/10/26
N2 - Face clustering and face tracking are two areas of active research in automatic facial video processing. They, however, have long been studied separately, despite the inherent link between them. In this paper, we propose to perform simultaneous face clustering and face tracking from real world videos. The motivation for the proposed research is that face clustering and face tracking can provide useful information and constraints to each other, thus can bootstrap and improve the performances of each other. To this end, we introduce a Coupled Hidden Markov Random Field (CHMRF) to simultaneously model face clustering, face tracking, and their interactions. We provide an effective algorithm based on constrained clustering and optimal tracking for the joint optimization of cluster labels and face tracking. We demonstrate significant improvements over state-of-the-art results in face clustering and tracking on several videos.
AB - Face clustering and face tracking are two areas of active research in automatic facial video processing. They, however, have long been studied separately, despite the inherent link between them. In this paper, we propose to perform simultaneous face clustering and face tracking from real world videos. The motivation for the proposed research is that face clustering and face tracking can provide useful information and constraints to each other, thus can bootstrap and improve the performances of each other. To this end, we introduce a Coupled Hidden Markov Random Field (CHMRF) to simultaneously model face clustering, face tracking, and their interactions. We provide an effective algorithm based on constrained clustering and optimal tracking for the joint optimization of cluster labels and face tracking. We demonstrate significant improvements over state-of-the-art results in face clustering and tracking on several videos.
UR - http://hdl.handle.net/10754/621254
UR - http://www.sciencedirect.com/science/article/pii/S0031320316303387
UR - http://www.scopus.com/inward/record.url?scp=85007339584&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2016.10.022
DO - 10.1016/j.patcog.2016.10.022
M3 - Article
SN - 0031-3203
VL - 64
SP - 361
EP - 373
JO - Pattern Recognition
JF - Pattern Recognition
ER -