Y
Yu Liu
Researcher at National University of Defense Technology
Publications - 99
Citations - 726
Yu Liu is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Image restoration & Sparse approximation. The author has an hindex of 11, co-authored 96 publications receiving 542 citations.
Papers
More filters
Proceedings ArticleDOI
MoNet: Deep Motion Exploitation for Video Object Segmentation
TL;DR: A novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i.e., frame representation learning and segmentation refinement, provides new state-of-the-art performance on three competitive benchmark datasets.
Proceedings ArticleDOI
Joint demosaicing and denoising of noisy bayer images with ADMM
TL;DR: A unified object function with hidden priors and a variant of ADMM to recover a full-resolution color image with a noisy Bayer input and demonstrates that this method performs better than state-of-the-art methods in both PSNR comparison and human vision and is much more robust to variations of noise level.
Journal ArticleDOI
Large range modification of exciton species in monolayer WS 2 .
TL;DR: In this paper, the binding energy of trion was determined to be ∼26 meV and independent of temperature, indicating strong Coulomb interaction of carriers in such 2D materials, and the resonance energy of the excitons and trions showed redshifts with increasing temperature due to electron-phonon coupling.
Journal ArticleDOI
Giant photoluminescence enhancement in monolayer WS_2 by energy transfer from CsPbBr_3 quantum dots
TL;DR: In this paper, a type I heterostructure geometry comprising of transition metal dichalcogenides (TMDCs) and lead halide perovskite quantum dots (QDs) was proposed to improve the performance of the TMDC-based optoelectronic devices.
Journal ArticleDOI
Online Meta Adaptation for Fast Video Object Segmentation
TL;DR: In this paper, a meta-learner is trained on multiple VOS tasks such that the meta model can capture their common knowledge and gains the ability to fast adapt the segmentation model to new video sequences.