Journal of Electronic Imaging 2021

11 papers
The 2021 edition of the Journal of Electronic Imaging emphasized advancements in ghost-free high dynamic range (HDR) imaging for dynamic scenes. Research during this period frequently utilized deep learning architectures, such as attention modules for facial expression recognition and self-supervised networks for monocular depth estimation. Notable contributions included the development of the TAMNet architecture and the MonodepthPlus framework, which incorporates soft-attention and outlier-masking techniques for improved depth accuracy. The year also saw developments in image reconstruction and data representation. This included adaptive inpainting algorithms using kriging pretreatment and tensor dispersion-based feature embedding for dimension reduction. Video compression was another area of focus, specifically fast 3D-HEVC depth map intracoding using convolutional neural networks. Prolific contributors included researchers such as Jie Shao, Hongbin Han, and Ruyi Han, who explored diverse topics ranging from multi-density peaks clustering to robust target tracking via Siamese networks combined with long short-term memory. These works reflect a broader trend toward integrating structural modeling with neural networks to enhance image analysis and processing efficiency.

Top Research Directions

The 1 research directions with Journal of Electronic Imaging 2021 papers, ranked by paper count, next to 2020. Share is the fraction of the edition’s papers in the direction.

#Direction20212020Share 2021Share 20202020 rank
1Deghosting Multi Exposure Images in Dynamic Scenes109.1%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Journal of Electronic Imaging 2021 papers: a paper credits every institution named in its affiliations, once. 1 institutions share 1 credited papers.

#InstitutionPapersShare
1Saarland University 1100.0%

Download all institutions as CSV

About this data

Papers. Journal of Electronic Imaging 2021 lists 11 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2020 use shares, since the edition went from 4 to 11 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 1 of 11 papers (9.1%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of Electronic Imaging 2021”, https://lacuna.tiptreesystems.com/venue/journal-of-electronic-imaging/2021.

Top Authors

AuthorPapers
Ning Jia1

Impactful Papers

Papers from Journal of Electronic Imaging 2021 that shaped research clusters.

Influential

Papers

Title
Adaptive coding unit size convolutional neural network for fast 3D-HEVC depth map intracoding
Adaptive image inpainting algorithm based on sample block by kriging pretreatment and facet model
EnsembleDet: ensembling against adversarial attack on deepfake detection
Long short-term memory improved Siamese network for robust target tracking
MonodepthPlus: self-supervised monocular depth estimation using soft-attention and learnable outlier-masking
Multi-density peaks clustering superpixel
Multidimensional sentiment recognition of film and television scene images
Removing multi-frame Gaussian noise by combining patch-based filters with optical flow
Robust local binary descriptor in rotation change using polar location
TAMNet: two attention modules-based network on facial expression recognition under uncertainty
Tensor dispersion-based multi-view feature embedding for dimension reduction