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.
Top Authors
Impactful Papers
Papers from IEEE TIP 2017 that shaped research clusters.
Foundational
Gradient-Based Tone Mapping for Rate-Distortion Optimized Backward-Compatible High Dynamic Range Com
foundational
Joint Luminance and Chrominance Optimiza
Learning Correspondence Structures for Person Re-Identification
foundational
Category Level 6D Object Pose Estimation
Influential
Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach
influential
Deghosting Multi Exposure Images in Dyna
Blind Facial Image Quality Enhancement using Non-Rigid Semantic Patches
influential
Restoring Images with Unknown Complex De
Segmenting Multi-Source Images Using Hidden Markov Fields With Copula-Based Multivariate Statistical
influential
Modeling Joint Extremes through Tail Dep
Deep Aesthetic Quality Assessment With Semantic Information
influential
Category Specific Image Aesthetic Assess
A Parallel Proximal Algorithm for Anisotropic Total Variation Minimization
influential
Parallelized Compressive Sensing
Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient La
influential
Biometric Recognition with a Single Samp
Out-of-Sample Extension for Dimensionality Reduction of Noisy Time Series
influential
Temporal Smoothness Regularization in Se
Learning Correspondence Structures for Person Re-Identification
influential
Spatially Aligning Features for Person R
Locally-Supervised Deep Hybrid Model for Scene Recognition
influential
Preserving Tiny Features Against Spatial
Clearing the Skies: A deep network architecture for single-image rain removal
influential
Overcoming the Iterative Bottleneck in S