activity
20162021
most citedDeep Learning for Scene Classification: A Survey

22 citations · 25 across the 3 of their papers we have counts for

collaborators

5 papers

eess.IV2021

Self-Verification in Image Denoising

Huangxing Lin, Yihong Zhuang, Delu Zeng +3

We devise a new regularization, called self-verification, for image denoising. This regularization is formulated using a deep image prior learned by the network, rather than a trad…

cs.CV202122 cited

Deep Learning for Scene Classification: A Survey

Delu Zeng, Minyu Liao, Mohammad Tavakolian +5

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challengin…

cs.GR20193 cited

Scan-flood Fill(SCAFF): an Efficient Automatic Precise Region Filling Algorithm for Complicated Regions

Yixuan He, Tianyi Hu, Delu Zeng

Recently, instant level labeling for supervised machine learning requires a considerable number of filled masks. In this paper, we propose an efficient automatic region filling alg…

cs.CV2018

Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation

Delu Zeng, Yixuan He, Li Liu +4

Although deep CNNs have brought significant improvement to image saliency detection, most CNN based models are sensitive to distortion such as compression and noise. In this paper,…

cs.CV2016

Saliency Detection with Spaces of Background-based Distribution

Tong Zhao, Lin Li, Xinghao Ding +2

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches…