IEEE TIP 2015

326 papers
In 2015, IEEE Transactions on Image Processing published research focused on high-dimensional data analysis, computational efficiency, and robust computer vision. Key theoretical themes included all-or-nothing phase transitions in inference, lattice quantization for neural compression, and dimensionality reduction via sparse random matrices. Significant contributions were made in scaling Gaussian processes and developing stable linear algebra for high-dimensional applications. Prolific authors such as Yunhong Wang, Ling Shao, and Rama Chellappa explored scalable video analysis and hierarchical decompositions for non-rigid motion. Applied research during this period addressed complex imaging challenges, including face recognition under non-uniform motion blur and pose variations. Notable work covered texture-independent long-term tracking, multiscale image denoising, and high-resolution light field capture using coded apertures. The edition also featured advancements in hyperspectral remote sensing via nonlinear unmixing and the extraction of curve-like structures through minimal path propagation. These studies collectively advanced the modeling of natural image statistics and the understanding of fine-grained temporal actions.

Top Research Directions

Research directions most represented by IEEE TIP 2015 papers.

The Fragility of Boundary Priors in Computer Vision 2
Separating Foreground Motion from Stochastic Background Clutter 2
Overcoming the Rank Bottleneck in Discriminant Dimensionality Reduction 1
Overcoming the Class Count Bottleneck in Discriminant Analysis 1
Optimization of Nondecomposable Performance Metrics 1
Resolving the Hollow Effect in Object Saliency Maps 1
Image Boundaries as Background Priors 1
The Efficiency Accuracy Trade Off in Dimensionality Reduction 1
Anticipating Upcoming Structures in Incremental Language Parsing 1
Nonnegative Spectral Relaxation for Direct Cluster Assignment 1
Amortized Inference for Sparse Coding 1
High-Dimensional Lattice Quantization 1
Unsupervised Learning of Convolutional Filters from Local Patches 1
Hierarchical Bayesian Parameter Estimation through Partial Pooling 1
End-to-End Representation Learning for Video Understanding 1

Top Authors

AuthorPapers
Dacheng Tao15
Xuelong Li8
Alan Bovik7
Zhou Wang7
Rama Chellappa6
Shuicheng YAN6
Xinbo Gao6
Junsong Yuan5
Ling Shao5
Zhouchen Lin5
Huchuan Lu4
Jinhui Tang4
Meng Wang4
Ming-Hsuan Yang4
Richang Hong4
Wei Liu4
Bumsub Ham3
Dongbo Min3
Kede Ma3
Kwanghoon Sohn3

Impactful Papers

Papers from IEEE TIP 2015 that shaped research clusters.

Foundational

Influential

Papers

Title
Human Facial Expression Recognition Using Stepwise Linear Discriminant Analysis and Hidden Conditional Random Fields
Hyperspectral Face Recognition With Spatiospectral Information Fusion and PLS Regression
Identification of Transform Coding Chains
Image Annotation by Latent Community Detection and Multikernel Learning
Image Denoising by Exploring External and Internal Correlations
Image Location Estimation by Salient Region Matching
Image Outlier Detection and Feature Extraction via L1-Norm-Based 2D Probabilistic PCA
Image Segmentation Using Hierarchical Merge Tree
Image-Specific Prior Adaptation for Denoising
Inner and Inter Label Propagation: Salient Object Detection in the Wild
Integrated Foreground Segmentation and Boundary Matting for Live Videos
Interactive Cosegmentation Using Global and Local Energy Optimization
Inverse Sparse Tracker With a Locally Weighted Distance Metric
JF-Cut: A Parallel Graph Cut Approach for Large-Scale Image and Video
Joint Group Sparse PCA for Compressed Hyperspectral Imaging
Joint Sparse Representation and Robust Feature-Level Fusion for Multi-Cue Visual Tracking
Large-Scale Weakly Supervised Object Localization via Latent Category Learning
Layered Compression for High-Precision Depth Data
Learning a Nonnegative Sparse Graph for Linear Regression
Learning Compact Feature Descriptor and Adaptive Matching Framework for Face Recognition
Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition
Learning Multiple Linear Mappings for Efficient Single Image Super-Resolution
Learning Person-Person Interaction in Collective Activity Recognition
Learning Sample Specific Weights for Late Fusion
Learning Super-Resolution Jointly From External and Internal Examples
Learning Templates for Artistic Portrait Lighting Analysis
Learning to Rank Image Tags With Limited Training Examples
Learning View-Model Joint Relevance for 3D Object Retrieval
Local Multi-Grouped Binary Descriptor With Ring-Based Pooling Configuration and Optimization
Local Sparse Structure Denoising for Low-Light-Level Image
Low-Rank Prior in Single Patches for Nonpointwise Impulse Noise Removal
Machine Learning-Based Coding Unit Depth Decisions for Flexible Complexity Allocation in High Efficiency Video Coding
Manifold Kernel Sparse Representation of Symmetric Positive-Definite Matrices and Its Applications
Markov Network-Based Unified Classifier for Face Recognition
Matching Images With Multiple Descriptors: An Unsupervised Approach for Locally Adaptive Descriptor Selection
Max-Confidence Boosting With Uncertainty for Visual Tracking
Merge Frame Design for Video Stream Switching using Piecewise Constant Functions
Micro-Expression Recognition Using Color Spaces
Missing Modality Transfer Learning via Latent Low-Rank Constraint
Modeling Neuron Selectivity Over Simple Midlevel Features for Image Classification
Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification
Multimodal Deep Autoencoder for Human Pose Recovery
Multimodal Registration via Mutual Information Incorporating Geometric and Spatial Context
Multiresolution Graph Fourier Transform for Compression of Piecewise Smooth Images
Multiscale Image Blind Denoising
Multiscale Logarithm Difference Edgemaps for Face Recognition Against Varying Lighting Conditions
Multispectral Image Out-of-Focus Deblurring Using Interchannel Correlation
Multi-Task Pose-Invariant Face Recognition
Multiview Alignment Hashing for Efficient Image Search
Multi-View Learning With Incomplete Views

« prev Page 4/7 next »