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
The Visual Word Booster: A Spatial Layout of Words Descriptor Exploiting Contour Cues
Too Far to See? Not Really! - Pedestrian Detection With Scale-Aware Localization Policy
Towards a Closed Form Second-Order Natural Scene Statistics Model
Towards Edge-Aware Spatio-Temporal Filtering in Real-Time
Toward the Repeatability and Robustness of the Local Reference Frame for 3D Shape Matching: An Evaluation
Training Very Deep CNNs for General Non-Blind Deconvolution
Transportation Spherical Watermarking
Triplet-Based Deep Hashing Network for Cross-Modal Retrieval
Uncertainty-Based Active Learning via Sparse Modeling for Image Classification
Unified Discriminative and Coherent Semi-Supervised Subspace Clustering
Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval
Unsupervised Online Video Object Segmentation With Motion Property Understanding
Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
Unsupervised Uncertainty Estimation Using Spatiotemporal Cues in Video Saliency Detection
USEAQ: Ultra-Fast Superpixel Extraction via Adaptive Sampling From Quantized Regions
Variational Decompression of Image Data From DjVu Encoded Files
Vehicle Re-Identification by Deep Hidden Multi-View Inference
Video-Based Person Re-Identification by Simultaneously Learning Intra-Video and Inter-Video Distance Metrics
Video Captioning by Adversarial LSTM
Video Salient Object Detection via Fully Convolutional Networks
Video Summarization Via Multiview Representative Selection
Video Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network
Video Synopsis in Complex Situations
Visual Representation and Classification by Learning Group Sparse Deep Stacking Network
Visual Tracking Under Motion Blur
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning
VRSA Net: VR Sickness Assessment Considering Exceptional Motion for 360° VR Video
Weighted Large Margin Nearest Center Distance-Based Human Depth Recovery With Limited Bandwidth Consumption
When Dijkstra Meets Vanishing Point: A Stereo Vision Approach for Road Detection
Zero-Shot Learning via Attribute Regression and Class Prototype Rectification
Zero-Shot Learning via Robust Latent Representation and Manifold Regularization

« prev Page 8/8