no code implementations • 29 Jul 2019 • Xuelong. Li, Hongli Li, Yongsheng Dong
Particularly, MetaL-TDVS aims to excavate the latent mechanism for summarizing video by reformulating video summarization as a meta learning problem and promote generalization ability of the trained model.
no code implementations • 28 Apr 2019 • Xuelong. Li, Quanmao Lu, Yongsheng Dong, DaCheng Tao
This is due to that the CLF's influence function has a upper bound which can alleviate the influence of a single sample, especially the sample with a large noise, on estimating the residuals.
no code implementations • 17 Apr 2019 • Xuelong. Li, Quanmao Lu, Yongsheng Dong, DaCheng Tao
Moreover, considering the importance of the discriminative information underlying in the initial clustering results, we add a discriminative constraint into our proposed objective function.
no code implementations • 16 Apr 2019 • Xuelong. Li, Kang Liu, Yongsheng Dong, DaCheng Tao
In this paper, a manifold matting framework named Patch Alignment Manifold Matting is proposed for image matting.
no code implementations • 16 Apr 2019 • Mingxin Jin, Yongsheng Dong, Lintao Zheng, Lingfei Liang, Tianyu Wang, Hongyan zhang
Color texture representation is an important step in the task of texture classification.