A Two-Stage Clustering Based 3D Visual Saliency Model for Dynamic Scenarios

You, Yang; Li, Bei; Li, Pian; Liu, Qiong

doi:10.1109/tmm.2018.2867742

Cited by 39 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The clustering‐based methods are the extension of clustering methods for 2D images [8]. As a typical representative of the clustering‐based methods, J‐linkage [9, 10] fulfils multi‐model fitting by merging models and their inliers with a threshold of Jaccard distance, and then updating models with merged point sets.…”

Section: Related Workmentioning

confidence: 99%

Energy minimisation‐based multi‐class multi‐instance geometric primitives extraction from 3D point clouds

et al. 2020

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Energy minimisation‐based multi‐class multi‐instance geometric primitives extraction from 3D point clouds

et al. 2020

View full text Add to dashboard Cite

“…In recent years, image and video acquisition, processing, and analysis have commanded greater focus from researchers [12][13][14][15][16]. A significant amount of work has taken place analyzing ISR, with Wang et al [16] producing a review of this body of work.…”

Section: Related Workmentioning

confidence: 99%

A multiresolution mixture generative adversarial network for video super-resolution

Tian

Wang

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

Generative adversarial networks (GANs) have been used to obtain super-resolution (SR) videos that have improved visual perception quality and more coherent details. However, the latest methods perform poorly in areas with dense textures. To better recover the areas with dense textures in video frames and improve the visual perception quality and coherence in videos, this paper proposes a multiresolution mixture generative adversarial network for video super-resolution (MRMVSR). We propose a multiresolution mixture network (MRMNet) as the generative network that can simultaneously generate multiresolution feature maps. In MRMNet, the high-resolution (HR) feature maps can continuously extract information from low-resolution (LR) feature maps to supplement information. In addition, we propose a residual fluctuation loss function for video super-resolution. The residual fluctuation loss function is used to reduce the overall residual fluctuation on SR and HR video frames to avoid a scenario where local differences are too large. Experimental results on the public benchmark dataset show that our method outperforms the state-of-the-art methods for the majority of the test sets.

show abstract

“…Witnessed by the rapid development of computer graphics, information science and other related technologies these years, three‐dimensional shape retrieval has gradually become a research focus of computer vision. For instance, it can be applied in fields such as biometric identification [1–3], image analysis [4, 5], e‐commerce [6, 7], virtual reality [8–10] etc. Biological individual identification, especially in the field of forensic science, is a research with important application value [11, 12].…”

Section: Introductionmentioning

confidence: 99%

Individual retrieval based on oral cavity point cloud data and correntropy‐based registration algorithm

Cui

Liu

et al. 2020

IET image process

View full text Add to dashboard Cite

A Two-Stage Clustering Based 3D Visual Saliency Model for Dynamic Scenarios

Cited by 39 publications

References 54 publications

Energy minimisation‐based multi‐class multi‐instance geometric primitives extraction from 3D point clouds

Energy minimisation‐based multi‐class multi‐instance geometric primitives extraction from 3D point clouds

A multiresolution mixture generative adversarial network for video super-resolution

Individual retrieval based on oral cavity point cloud data and correntropy‐based registration algorithm

Contact Info

Product

Resources

About