Y
Yuanjie Shao
Researcher at Huazhong University of Science and Technology
Publications - 42
Citations - 560
Yuanjie Shao is an academic researcher from Huazhong University of Science and Technology. The author has contributed to research in topics: Sparse approximation & Image restoration. The author has an hindex of 7, co-authored 39 publications receiving 226 citations.
Papers
More filters
Proceedings ArticleDOI
Domain Adaptation for Image Dehazing
TL;DR: Zhang et al. as mentioned in this paper proposed a domain adaptation paradigm consisting of an image translation module and two image dehazing modules, which can bridge the gap between the synthetic and real domains by translating images from one domain to another.
Posted Content
Domain Adaptation for Image Dehazing
TL;DR: This work proposes a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules, and applies a bidirectional translation network to bridge the gap between the synthetic and real domains by translating images from one domain to another.
Journal ArticleDOI
Probabilistic class structure regularized sparse representation graph for semi-supervised hyperspectral image classification
TL;DR: By incorporating the class structure information into the SR model, PCSSR can learn a discriminative graph from the data and outperforms state of the art methods on Hyperion and AVIRIS hyperspectral data.
Proceedings ArticleDOI
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
TL;DR: Wang et al. as discussed by the authors proposed a self-supervised semi supervised temporal action proposal (SSTAP) framework, which contains two crucial branches, i.e., a temporal-aware semisupervised branch and a relation-aware self supervised branch, to learn the relation of temporal clues.
Journal ArticleDOI
GTNet: Generative Transfer Network for Zero-Shot Object Detection
TL;DR: An IoU-Aware Generative Adversarial Network (IoUGAN) is designed as the feature synthesizer, which can be easily integrated into GTNet, and performs favorably against the state-of-the-art ZSD approaches.