J
Jiawei Wu
Researcher at Politehnica University of Timișoara
Publications - 7
Citations - 38
Jiawei Wu is an academic researcher from Politehnica University of Timișoara. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 1, co-authored 1 publications receiving 16 citations.
Papers
More filters
Proceedings ArticleDOI
NTIRE 2019 Image Dehazing Challenge Report
Codruta O. Ancuti,Cosmin Ancuti,Radu Timofte,Luc Van Gool,Lei Zhang,Ming-Hsuan Yang,Tiantong Guo,Xuelu Li,Venkateswararao Cherukuri,Vishal Monga,Hao Jiang,Siyuan Yang,Yan Liu,Xiaochao Qu,Pengfei Wan,Dongwon Park,Se Young Chun,Ming Hong,Jinying Huang,Yizi Chen,Shuxin Chen,Bomin Wang,Pablo Navarrete Michelini,Hanwen Liu,Dan Zhu,Jing Liu,Sanchayan Santra,Ranjan Mondal,Bhabatosh Chanda,Peter Morales,Tzofi Klinghoffer,Le Manh Quan,Yong-Guk Kim,Xiao Liang,Runde Li,Jinshan Pan,Jinhui Tang,Kuldeep Purohit,Maitreya Suin,A. N. Rajagopalan,Raimondo Schettini,Simone Bianco,Flavio Piccoli,C. Cusano,Luigi Celona,Sunhee Hwang,Yu Seung Ma,Hyeran Byun,Subrahmanyam Murala,Akshay Dudhane,Harsh Aulakh,Tianxiang Zheng,Tao Zhang,Weining Qin,Runnan Zhou,Shanhu Wang,Jean-Philippe Tarel,Chuansheng Wang,Jiawei Wu +58 more
TL;DR: This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results and gauge the state-of-the-art in imageDehazing.
Journal ArticleDOI
Semi-Supervised Leukocyte Segmentation Based on Adversarial Learning With Reconstruction Enhancement
TL;DR: Quantitative and qualitative experimental results demonstrate the superiority of the proposed semisupervised leukocyte segmentation method over several state-of-the-art methods, achieving the highest average $F1$ score and mIoU of 0.9493 with only 20% labeled training samples.
Journal ArticleDOI
Information Transfer in Semi-supervised Semantic Segmentation
TL;DR: In this paper , the authors proposed an information transfer theory to align different types of information for semi-supervised semantic segmentation and achieved state-of-the-art performance.
Journal ArticleDOI
Study on Mechanical Properties of Composite Foundation with Rigid Pile Based on the Cushion and Strength Adjustor Control
TL;DR: In this paper , a deformation adjustor based on strengths used in composite foundations is proposed, in which foam slabs with different yield strengths are placed on the top of the pile to coordinate the pile-soil deformation.
Journal ArticleDOI
Foreground–background decoupling matting
TL;DR: Zhang et al. as mentioned in this paper proposed a new set of matting subtasks, including foreground segmentation, background segmentation and disambiguation, to address the dependency of priors.