IEEE TIP 2018

381 papers
The 2018 volume of IEEE Transactions on Image Processing featured 33 papers centered on video quality assessment, knowledge distillation, and computational efficiency. A significant portion of the research addressed the evaluation of real-world user-generated content, incorporating human memory models and large-scale perceptual studies. Knowledge distillation emerged as a prominent theme, with studies exploring its application in denoising for weak-to-strong generalization and selective feature distillation for task-relevant learning. The edition also highlighted advancements in resource-constrained imaging, featuring lightweight convolutional architectures for real-time edge computing and visual recognition in extremely low-resolution settings. Methodological contributions included uncertainty-based active learning via sparse modeling, game theory-inspired binarization for degraded documents, and multi-atlas registration for pathological images. Prolific authors such as Ming-Hsuan Yang, Bin Liu, and Si Liu contributed to these areas, alongside research into quality control for crowdsourced data labeling and robust display-to-camera communications via blue channel embedding.

Top Research Directions

Research directions most represented by IEEE TIP 2018 papers.

Preserving Neighborhood Structure in Binary Hashing 2
Neural Similarity Learning with Trainable Metrics 2
Content Adaptive Image Partitioning 2
The Fragility of Boundary Priors in Computer Vision 2
Iterative Attention Refinement across Network Layers 2
Mitigating Sequential Error Propagation in Multi Stage Pipelines 2
Asymmetric Computational Complexity in Neural Compression 2
Flexible Geometric Modeling for Arbitrary Shaped Text Detection 2
Deep Unfolding Networks for Inverse Problems 2
Modeling Non-Gaussian Noise in Signal Restoration 2
Eliminating the Optical Flow Bottleneck in Video Understanding 2
Overcoming the Computational Overhead of Deep Features 2
Learning Oriented Bounding Boxes for Arbitrary Object Detection 2
Overcoming the Iterative Bottleneck in Sparse Representation 2
Preserving Tiny Features Against Spatial Resolution Degradation 2

Top Authors

AuthorPapers
Dacheng Tao10
Ming-Hsuan Yang10
Junwei Han9
Ling Shao9
Wen Gao8
Yun Fu7
Alan Bovik5
Jungong Han5
Junsong Yuan5
Shiqi Wang5
Shuicheng YAN5
Xuelong Li5
Zhengming Ding5
Jian Yang4
Jiashi Feng4
LINGYU DUAN4
Qionghai Dai4
Ruiqin Xiong4
Wangmeng Zuo4
Xinbo Gao4

Impactful Papers

Papers from IEEE TIP 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Generative Model With Coordinate Metric Learning for Object Recognition Based on 3D Models
Geometry-Consistent Light Field Super-Resolution via Graph-Based Regularization
Glass Reflection Removal Using Co-Saliency-Based Image Alignment and Low-Rank Matrix Completion in Gradient Domain
Global-Local Temporal Saliency Action Prediction
Globally Variance-Constrained Sparse Representation and Its Application in Image Set Coding
Grid-Free Localization Algorithm Using Low-Rank Hankel Matrix for Super-Resolution Microscopy
Halftone Image Watermarking by Content Aware Double-Sided Embedding Error Diffusion
Hallucinating Face Image by Regularization Models in High-Resolution Feature Space
Hashing with Angular Reconstructive Embeddings
Heteroscedastic Max-Min Distance Analysis for Dimensionality Reduction
Hierarchical and Spatio-Temporal Sparse Representation for Human Action Recognition
Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features
Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning
High-Order Model and Dynamic Filtering for Frame Rate Up-Conversion
High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity
HMS-Net: Hierarchical Multi-Scale Sparsity-Invariant Network for Sparse Depth Completion
Holistic Multi-Modal Memory Network for Movie Question Answering
Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning
How Does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution
Human Motion Segmentation via Robust Kernel Sparse Subspace Clustering
Hybrid All Zero Soft Quantized Block Detection for HEVC
Hyper-Lapse From Multiple Spatially-Overlapping Videos
Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network
Hyperspectral Image Super-Resolution With a Mosaic RGB Image
GiB: A ${G}$ ame Theory ${I}$ nspired ${B}$ inarization Technique for Degraded Document Images
Image Haze Removal via Reference Retrieval and Scene Prior
Image Provenance Analysis at Scale
Image Regularizations Based on the Sparsity of Corner Points
Image Super-Resolution With Parametric Sparse Model Learning
Imagining the Unimaginable Faces by Deconvolutional Networks
Implicit Block Diagonal Low-Rank Representation
Implicit Negative Sub-Categorization and Sink Diversion for Object Detection
Improved Bilateral Texture Filtering With Edge-Aware Measurement
Inductive Multi-Hypergraph Learning and Its Application on View-Based 3D Object Classification
Interacting Tracklets for Multi-Object Tracking
Investigating Nuisances in DCNN-Based Face Recognition
IPAD: Intensity Potential for Adaptive De-Quantization
IPST: Incremental Pictorial Structures for Model-Free Tracking of Deformable Objects
Iterative Graph Seeking for Object Tracking
Joint Denoising/Compression of Image Contours via Shape Prior and Context Tree
Joint Hand Detection and Rotation Estimation Using CNN
Joint Hypergraph Learning for Tag-Based Image Retrieval
Jointly Sparse Hashing for Image Retrieval
Joint Separable and Non-Separable Transforms for Next-Generation Video Coding
Joint Tumor Segmentation in PET-CT Images Using Co-Clustering and Fusion Based on Belief Functions
Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks
Knowledge-Based Topic Model for Unsupervised Object Discovery and Localization
L0-Regularized Image Downscaling
ℓ2, p -Norm Based PCA for Image Recognition
Landmark-Based Shape Encoding and Sparse-Dictionary Learning in the Continuous Domain

« prev Page 4/8 next »