ICIP 2016
371 papers
The 2016 edition of ICIP featured 466 papers covering developments in motion estimation, sparse signal reconstruction, and image restoration. Research themes emphasized improving visual object tracking by preventing model drift and developing efficient motion representations that bypass explicit optical flow. Notable work addressed low-rank and sparse matrix decomposition, alongside automated parameter learning in message passing algorithms and the exploitation of group structures in signal recovery.
Methodological trends included the integration of graph Fourier transforms for subspace-sparsifying transforms and the use of weakly supervised learning for semantic segmentation and human activity recognition. Applications spanned diverse domains, such as pedestrian detection using physiological frameworks, saliency detection in 3D point clouds, and handwritten character recognition. Prolific contributors to this edition included David A. Clausi, Aggelos K. Katsaggelos, and Alexander Wong. The proceedings reflected a focus on spatially adaptive parameter maps and robust Bayesian methods for signal recovery, particularly for applications in face recognition.
Top Research Directions
Research directions most represented by ICIP 2016 papers.
Top Authors
Impactful Papers
Papers from ICIP 2016 that shaped research clusters.
Influential
How deep neural networks can improve emotion recognition on video data
influential
Modeling the Temporal Evolution of Facia
SSSC-AM: A unified framework for video co-segmentation by structured sparse subspace clustering with
influential
Jointly Optimizing Representations and C
Mutual exclusivity loss for semi-supervised deep learning
influential
Overcoming the Data Annotation Bottlenec
How deep neural networks can improve emotion recognition on video data
influential
The Critical Role of Systematic Hyperpar
Mutual exclusivity loss for semi-supervised deep learning
influential
The Sensitivity of Multi-Objective Loss
Hyperspectral image classification with support vector machines on kernel distribution embeddings
influential
Scaling Kernel Methods with Random Fouri
Persistent Homology of Attractors For Action Recognition
influential
Robust Feature Extraction for Unconstrai
Unsupervised convolutional neural networks for motion estimation
influential
Coarse to Fine Refinement for Motion Est
Completed local derivative pattern for rotation invariant texture classification
influential
Rotation Invariant Local Texture Descrip
Papers
« prev Page 8/8