TY - JOUR
T1 - Sequential Clique Optimization for Unsupervised and Weakly Supervised Video Object Segmentation
AU - Koh, Yeong Jun
AU - Heo, Yuk
AU - Kim, Chang Su
N1 - Funding Information:
This work was partly supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (NRF-2021R1A4A1031864), Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2022R1I1A3069113), Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. RS-2022-00155857, Artificial Intelligence Convergence Innovation Human Resources Development (Chungnam National University)), and Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-01441, Artificial Intelligence Convergence Research Center (Chungnam National University)).
Publisher Copyright:
© 2022 by the authors.
PY - 2022/9
Y1 - 2022/9
N2 - A novel video object segmentation algorithm, which segments out multiple objects in a video sequence in unsupervised or weakly supervised manners, is proposed in this work. First, we match visually important object instances to construct salient object tracks through a video sequence without any user supervision. We formulate this matching process as the problem to find maximal weight cliques in a complete k-partite graph and develop the sequential clique optimization algorithm to determine the cliques efficiently. Then, we convert the resultant salient object tracks into object segmentation results and refine them based on Markov random field optimization. Second, we adapt the sequential clique optimization algorithm to perform weakly supervised video object segmentation. To this end, we develop a sparse-to-dense network to convert the point cliques into segmentation results. The experimental results demonstrate that the proposed algorithm provides comparable or better performances than recent state-of-the-art VOS algorithms.
AB - A novel video object segmentation algorithm, which segments out multiple objects in a video sequence in unsupervised or weakly supervised manners, is proposed in this work. First, we match visually important object instances to construct salient object tracks through a video sequence without any user supervision. We formulate this matching process as the problem to find maximal weight cliques in a complete k-partite graph and develop the sequential clique optimization algorithm to determine the cliques efficiently. Then, we convert the resultant salient object tracks into object segmentation results and refine them based on Markov random field optimization. Second, we adapt the sequential clique optimization algorithm to perform weakly supervised video object segmentation. To this end, we develop a sparse-to-dense network to convert the point cliques into segmentation results. The experimental results demonstrate that the proposed algorithm provides comparable or better performances than recent state-of-the-art VOS algorithms.
KW - convolutional neural networks
KW - primary object segmentation
KW - salient object detection
KW - sequential clique optimization
KW - video object segmentation
UR - http://www.scopus.com/inward/record.url?scp=85138691281&partnerID=8YFLogxK
U2 - 10.3390/electronics11182899
DO - 10.3390/electronics11182899
M3 - Article
AN - SCOPUS:85138691281
SN - 2079-9292
VL - 11
JO - Electronics (Switzerland)
JF - Electronics (Switzerland)
IS - 18
M1 - 2899
ER -