ICIP

8,285 papers1,207 directions
ICIP is a long-standing venue for research in image processing and computer vision, with a publication history spanning from 1995 to the present. With a corpus of over 8,500 papers, it serves as a hub for the technical development of visual data analysis and representation. The venue features contributions from researchers such as Miki Haseyama, Takahiro Ogawa, and Aggelos K. Katsaggelos, reflecting its role in the signal processing and computer vision communities. The research published at ICIP covers a broad spectrum of topics, ranging from classical inverse problems to modern deep learning architectures. Key research directions include automated regularization tuning, diffusion priors for non-linear problems, and the use of spatially adaptive parameter maps for image restoration. The venue also addresses the intersection of machine learning and human perception, including the alignment of adversarial robustness and video quality metrics with human visual systems. Other significant areas include 3D point cloud processing, temporal redundancy reduction through predictive coding, and the lifting of 2D human poses into 3D space. Current trends at the venue highlight the application of efficient AI models, such as multi-teacher knowledge distillation for segmentation and token--sparsity frameworks for vision transformers. The venue also explores specialized tasks like composition-aware image cropping, text legibility in user-generated media, and anomaly detection. Furthermore, ICIP hosts critical evaluations of machine learning methodologies, including adversarial analyses of explanatory metrics and semantic-guided predictors for image compression.

Papers by Year

2026 1
2025 6
2024 238
2023 328
2022 390
2021 406
2020 324
2019 493
2018 362
2017 458
2016 371
2015 447
2014 484
2013 357
2012 275
2011 342
2010 432
2009 305
2008 248
2007 118
2006 208
2005 220
2004 235
2003 189
2002 181
2001 167
2000 160
1999 98
1998 110
1997 115
1996 103
1995 73
1994 82

Top Research Directions

Research directions most represented by papers from this venue.

Cross Dataset Validation for Robust Model Generalization 11
The Perceptual Misalignment of Image Quality Metrics 9
Deep Unfolding Networks for Inverse Problems 8
Composite Loss Functions for Perceptual Image Restoration 8
Eliminating the Optical Flow Bottleneck in Video Understanding 8
3D Convolutions for Spatiotemporal Feature Learning 8
Exploiting Temporal Redundancy in Video Neural Networks 8
Lightweight Deep Learning for Edge Deployment 8
Cross Task Generalization in Image Restoration 7
Preserving Topological Connectivity in Thin Structure Segmentation 7
Balancing Noise Suppression and Texture Preservation 7
Tuning-Free Image Restoration and Inverse Problems 7
Generalizing Deep Learning Methods Beyond Image Classification 7
Scaling Memory Banks for High Dimensional Features 6
Factorizing Convolutions into Spatial and Channel Operations 6

Top Authors

AuthorPapers
Alan Bovik85
Ahmet Murat Tekalp80
Rama Chellappa75
Miki Haseyama74
Kiyoharu Aizawa73
Aggelos Katsaggelos63
Takahiro Ogawa63
Gene Cheung56
Michael Unser50
Xiaolin Wu50
Tieniu Tan47
Nam Ik Cho45
Petros Maragos45
Kwanghoon Sohn44
Siwei Ma44
Alfred O. Hero43
Yong Man Ro42
Edwin Hancock41
Peter Eisert41
Zhou Wang41

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Double random scrambling encoding in the RPMPFrHT domain2017
Do we really need more training data for object localization2017
Edge/structure preserving smoothing via relativity-of-Gaussian2017
Efficient cloud detection in remote sensing images using edge-aware segmentation network and easy-to-hard training strategy2017
Efficient directional and L1-optimized intra-prediction for light field image compression2017
Efficiently building 3D line model with points2017
Efficient similarity learning for asymmetric hashing2017
Efficient symmetry-driven fully convolutional network for multimodal brain tumor segmentation2017
Elmnet: Feature learning using extreme learning machines2017
Encyclopedia enhanced semantic embedding for zero-shot learning2017
End-to-end binary representation learning via direct binary embedding2017
Energy based fast event retrieval in video with temporal match kernel2017
Enhanced dictionary pair learning sparse representation model for facial expression classification2017
Enhanced trajectory-based action recognition using human pose2017
Enhancing feature discrimination for unsupervised hashing2017
Enhancing the perception of a hazy visual world using a see-through head-mounted device2017
Ensemble of active contour based image segmentation2017
Estimation of signal-dependent noise level function using multi-column convolutional neural network2017
Exploiting probabilistic relationships between action concepts for complex event classification2017
Exploring the influence of feature representation for dictionary selection based video summarization2017
Extended conjugate polar fourier transforminconvolution network2017
Extending the FOV from disparity and color consistencies in multiview light fields2017
Extracting key frames from first-person videos in the common space of multiple sensors2017
Fabric defect detection based on improved low-rank and sparse matrix decomposition2017
Face hallucination using region-based deep convolutional networks2017
Face recognition by landmark pooling-based CNN with concentrate loss2017
Face recognition using multi-modal low-rank dictionary learning2017
Face spoofing detection by fusing binocular depth and spatial pyramid coding micro-texture features2017
Fast and reliable human action recognition in video sequences by sequential analysis2017
Fast camera fingerprint matching in very large databases2017
Fast template matching for intra prediction2017
Fitness heart rate measurement using face videos2017
Flicker removal and superpixel-based motion tracking for high speed videos2017
Foreground detection in camouflaged scenes2017
Foveated neural network: Gaze prediction on egocentric videos2017
Foveated nonlocal dual denoising2017
Fovea weighting of multiview computational displays for enhanced user experience2017
From foot to head: Active face finding using deep Q-learning2017
From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning2017
FSVO: Semi-direct monocular visual odometry using fixed maps2017
Fully connected CRF with data-driven prior for multi-class brain tumor segmentation2017
Fusing shape and motion matrices for view invariant action recognition using 3D skeletons2017
Fusion of multi-angular aerial images based on epipolar geometry and matrix completion2017
Gated additive skip context connection for object detection2017
Gaussian process dynamic modeling of bat flapping flight2017
Gender classification in live videos2017
Generating adaptive and robust filter sets using an unsupervised learning framework2017
Geometric distortion metrics for point cloud compression2017
Global quality of assessment and optimization for the backward-compatible stereoscopic display system2017
GPU Based fast MPEG-CDVS encoder2017

« prev Page 54/166 next »