IEEE TIP 2017

400 papers
The 2017 edition of IEEE Transactions on Image Processing featured 29 papers covering advancements in image segmentation, feature representation, and object detection. Research themes focused on boundary adherence in superpixel segmentation and hierarchical multi-scale feature fusion for dense prediction. Notable studies addressed camouflaged object detection and the preservation of fine-grained details in downsampled feature maps. The year also included contributions to medical imaging, such as vertex regression-based segmentation for radiotherapy planning, and the use of aesthetics evaluation for summarizing social media data. Methodological trends emphasized efficiency and spatial awareness, including the use of coordinate convolutions to break translation invariance and learnable spatial priors for saliency prediction. Prolific authors such as Fumin Shen, Jingwei Guan, and Nemo Chen explored topics like angular reconstructive embeddings for hashing and robust multi-focus image fusion. Other research investigated goal-directed human gaze patterns and methods for mitigating spatial bias in computer vision. These works collectively advanced visual representation through global context modeling and scene-adapted human detection, alongside developments in joint projection and low-rank dictionary learning for object classification.

Top Research Directions

Research directions most represented by IEEE TIP 2017 papers.

The Irreversible Bottleneck of Superpixel Boundary Errors 3
The Perceptual Misalignment of Image Quality Metrics 3
Preserving Tiny Features Against Spatial Resolution Degradation 3
Modeling Principal Point and Distortion Center Misalignment 2
Aggregating Local Features via Fisher Vectors 2
Residual Noise Estimation for Signal Restoration 2
Kernel Based Non-linear Feature Mapping 2
Overcoming the Gaussian Assumption in High-Dimensional Learning 2
Overcoming Local Receptive Field Constraints in Visual Models 2
Direct Discrete Optimization for Binary Representation Learning 2
Overcoming Inter-Class Visual Similarity in Image Representation 2
Overcoming the Iterative Bottleneck in Sparse Representation 2
Basins of Attraction in Nonconvex Optimization 2
Sample Selection Guided by Model Uncertainty 2
Learning from Incomplete Multimodal Data Streams 2

Top Authors

AuthorPapers
Dacheng Tao12
Xuelong Li10
Alan Bovik9
Ling Shao9
Shiqi Wang6
Zhou Wang6
Fumin Shen5
Heng Tao Shen5
Junwei Han5
Kede Ma5
Lei Zhang5
Michael Unser5
Zhouchen Lin5
Fatih Porikli4
Huchuan Lu4
Jie Zhou4
Jungong Han4
Meng Wang4
Richang Hong4
Shuicheng YAN4

Impactful Papers

Papers from IEEE TIP 2017 that shaped research clusters.

Foundational

Influential

Papers

Title
Structure-From-Motion in Spherical Video Using the von Mises-Fisher Distribution
Structure-Regularized Compressive Tracking With Online Data-Driven Sampling
Study of Temporal Effects on Subjective Video Quality of Experience
Style Transfer Via Texture Synthesis
SuperPatchMatch: An Algorithm for Robust Correspondences Using Superpixel Patches
Super-Resolution Person Re-Identification With Semi-Coupled Low-Rank Discriminant Dictionary Learning
Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval
Templateless Non-Rigid Reconstruction and Motion Tracking With a Single RGB-D Camera
Temporal Coherence-Based Deblurring Using Non-Uniform Motion Optimization
Temporally Dependent Rate-Distortion Optimization for Low-Delay Hierarchical Video Coding
Texture Characterization Using Shape Co-Occurrence Patterns
Textured Image Demoiréing via Signal Decomposition and Guided Filtering
Texture Reconstruction Guided by a High-Resolution Patch
The Recognition of the Point Symbols in the Scanned Topographic Maps
The Shape Interaction Matrix-Based Affine Invariant Mismatch Removal for Partial-Duplicate Image Search
TMAGIC: A Model-Free 3D Tracker
Too Far to See? Not Really! - Pedestrian Detection with Scale-aware Localization Policy
Toward More Accurate Iris Recognition Using Cross-Spectral Matching
Toward Optimal Manifold Hashing via Discrete Locally Linear Embedding
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
Tracking Based Multi-Orientation Scene Text Detection: A Unified Framework With Dynamic Programming
Transform Coding for Point Clouds Using a Gaussian Process Model
Tree Structure Sparsity Pattern Guided Convex Optimization for Compressive Sensing of Large-Scale Images
Turning Diffusion-Based Image Colorization Into Efficient Color Compression
Uncorrelated Component Analysis-Based Hashing
Understanding Symmetric Smoothing Filters: A Gaussian Mixture Model Perspective
Underwater Image Restoration Based on Image Blurriness and Light Absorption
Unified Blind Quality Assessment of Compressed Natural, Graphic, and Screen Content Images
Unifying the Video and Question Attentions for Open-Ended Video Question Answering
Unsupervised Hierarchical Dynamic Parsing and Encoding for Action Recognition
Unsupervised Multi-Class Co-Segmentation via Joint-Cut Over L1 -Manifold Hyper-Graph of Discriminative Image Regions
Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling With Reliable Object Proposals
Unsupervised Sequential Outlier Detection With Deep Architectures
Unsupervised Simplification of Image Hierarchies via Evolution Analysis in Scale-Sets Framework
Unsupervised t-Distributed Video Hashing and Its Deep Hashing Extension
Variational Decompression of Image Data From DjVu Encoded Files
Video-Based Pedestrian Re-Identification by Adaptive Spatio-Temporal Appearance Model
Videography-Based Unconstrained Video Analysis
Video Saliency Detection via Spatial-Temporal Fusion and Low-Rank Coherency Diffusion
Video Vectorization via Tetrahedral Remeshing
VIDOSAT: High-Dimensional Sparsifying Transform Learning for Online Video Denoising
Visual Attention Modeling for Stereoscopic Video: A Benchmark and Computational Model
Visual Tracking by Sampling in Part Space
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
Weakly Supervised Deep Matrix Factorization for Social Image Understanding
Weakly Supervised Multimodal Kernel for Categorizing Aerial Photographs
Weakly Supervised Part Proposal Segmentation From Multiple Images
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
Wide-Baseline Foreground Object Interpolation Using Silhouette Shape Prior
Zero-Shot Learning With Transferred Samples

« prev Page 8/8