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.

Alternating Optimization for Sparse Dictionary Learning 2
Eliminating the Optical Flow Bottleneck in Video Understanding 2
Error Accumulation and Model Drift in Online Learning 2
Analyzing Dynamical Systems through Phase Space Geometry 1
Mitigating Signaling Overhead in Adaptive Visual Compression 1
Quantization Interval Constraints for Signal Reconstruction 1
Perceptual Texture Masking 1
Locally Adaptive Distance Metrics 1
Rigid Body Motion Priors for 3D Scene Flow 1
Phase Space Reconstruction from Time Series Data 1
Overcoming Texture Induced Over Segmentation 1
Poisson Likelihood Modeling for Photon Limited Reconstruction 1
Scaling Optimal Transport via One-Dimensional Projections 1
The Dimensionality Trade-off in Random Feature Kernel Approximations 1
Shape Recognition from Fragmented Edge Maps 1

Top Authors

AuthorPapers
Aggelos Katsaggelos7
Amit Roy-Chowdhury5
Alexander Wong4
Bihan Wen4
David A. Clausi4
Jiaying Liu4
Mayank Vatsa4
Petros Maragos4
Richa Singh4
Yong Man Ro4
Atsushi Shimizu3
Bing Zeng3
Christian Desrosiers3
David Bull3
Debin Zhao3
Ehsan Hosseini-Asl3
Fan Zhang3
Gene Cheung3
Hongkai Xiong3
Houqiang Li3

Impactful Papers

Papers from ICIP 2016 that shaped research clusters.

Influential

Papers

Title
Scene-based low delay HEVC encoding framework based on transparent composite modeling
Scene text detection with extremal region based cascaded filtering
Screen content image quality assessment using edge model
Screen content image quality assessment via convolutional neural network
Seed growing for interactive image segmentation with geodesic voting
Self-restraint object recognition by model based CNN learning
Self-similarity measure for multi-modal image registration
Semantic context and depth-aware object proposal generation
Semantic highlight retrieval
Shape-included label-consistent discriminative dictionary learning: An approach to detect and segment multi-class objects in images
Shape matching using a self similar affine invariant descriptor
Shearlet-based reduced reference image quality assessment
Show me your body: Gender classification from still images
Sign language recognition based on adaptive HMMS with data augmentation
Sign language recognition with long short-term memory
Simple and efficient H.265/HEVC coding of fixed camera videos
Simple online and realtime tracking
Simultaneous forgery identification and localization in paintings using advanced correlation filters
Simultaneous linear separation and unmixing of fluorescent and reflective components from a single hyperspectral image
Single image restoration using scene ambient light differential
Sketch-based image retrieval via Siamese convolutional neural network
Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array
Spatio-temporal representation for face authentication by using multi-task learning with human attributes
Spatio-temporal saliency detection using abstracted fully-connected graphical models
SSSC-AM: A unified framework for video co-segmentation by structured sparse subspace clustering with appearance and motion features
Stem cell microscopic image segmentation using supervised normalized cuts
Structured low-rank recovery of piecewise constant signals with performance guarantees
Structure preserving single image super-resolution
Sub-partition reuse for fast optimal motion estimation in HEVC successive elimination algorithms
Subspace-sparsifying steerable discrete cosine transform from graph fourier transform
Super-resolution of compressed videos using convolutional neural networks
Supervoxel-based saliency detection for large-scale colored 3D point clouds
Temporally aligned pooling representation for video-based person re-identification
Tensor morphological profile for hyperspectral image classification
Text detection based on convolutional neural networks with spatial pyramid pooling
Text detection in manga by combining connected-component-based and region-based classifications
The common self-polar triangle of separate circles: Properties and applications to camera calibration
The log-normal distribution of the size of objects in daily meal images and its application to the efficient reduction of object proposals
Towards robust color recovery for high-capacity color QR codes
Towards temporal adaptive representation for video action recognition
Towards unsupervised open-set person re-identification
Triple local feature based collaborative representation for face recognition with single sample per person
Tube ConvNets: Better exploiting motion for action recognition
Turbo denoising for mobile photographic applications
Turning a denoiser into a super-resolver using plug and play priors
Two-stage pooling of deep convolutional features for image retrieval
Underwater image descattering and quality assessment
Underwater image restoration based on minimum information loss principle and optical properties of underwater imaging
Unsupervised convolutional neural networks for motion estimation
Unsupervised person re-identification with locality-constrained Earth Mover's distance

« prev Page 7/8 next »