activity
20182020
most citedJoint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts

18 citations · 34 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20203 cited

Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation

Mingmin Zhen, Shiwei Li, Lei Zhou +4

In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent corr…

cs.CV202010 cited

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

Jiaxiang Shang, Tianwei Shen, Shiwei Li +4

Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-…

cs.CV202018 cited

Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts

Mingmin Zhen, Jinglu Wang, Lei Zhou +5

In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. The critical component in the framework is the iterative pyramid c…

cs.CV2020

KFNet: Learning Temporal Camera Relocalization using Kalman Filtering

Lei Zhou, Zixin Luo, Tianwei Shen +5

Temporal camera relocalization estimates the pose with respect to each video frame in sequence, as opposed to one-shot relocalization which focuses on a still image. Even though th…

cs.CV20193 cited

Learning Fully Dense Neural Networks for Image Semantic Segmentation

Mingmin Zhen, Jinglu Wang, Lei Zhou +2

Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take adv…

cs.AI2018

End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion

Chao Shang, Yun Tang, Jing Huang +3

Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the curre…