CVIU

1,505 papers647 directions
Computer Vision and Image Understanding is a research venue focused on the development and application of algorithms for processing and interpreting visual data. The publication covers a wide range of topics within the field of artificial intelligence, specifically targeting the intersection of machine learning and visual perception. Its scope includes theoretical advancements in image analysis as well as practical implementations in diverse domains. Recent research published at this venue spans several specialized areas, including 3D reconstruction techniques like Gaussian Splatting for physics-based simulations and urban surface reconstruction using SAR tomography. The venue also features work on human-centric vision, such as full-body virtual try-on systems, 4D human video stylization, and action retrieval. Additionally, the publication addresses complex reasoning tasks like diagram question answering and security-focused topics such as adversarial attacks on object detection models. Between 2018 and 2026, the venue has seen contributions from several active researchers in the field, including Ming-Hsuan Yang, Pilsung Kang, and Przemysław Spurek. By hosting studies on multiple object tracking, transformer-based architectures, and assignment decision networks, the venue serves as a platform for disseminating technical developments in image understanding. The corpus reflects a consistent focus on evolving methodologies in both generative and discriminative computer vision tasks.

Papers by Year

2026 88
2025 95
2024 143
2023 95
2022 75
2021 79
2020 53
2019 54
2018 65
2017 91
2016 101
2015 60
2014 74
2013 59
2012 35
2011 63
2010 41
2009 39
2008 41
2007 27
2006 26
2005 14
2004 21
2003 20
2002 6
2001 17
2000 20
1999 19
1998 24
1997 32
1996 8
1995 13

Top Research Directions

Research directions most represented by papers from this venue.

Generalizing from Synthetic Data to the Real World 8
Eliminating the Optical Flow Bottleneck in Video Understanding 6
Adversarial Training for Domain Invariant Representations 6
Cross-Modal Attention Fusion for Heterogeneous Data Integration 6
Generalizing Deep Learning Methods Beyond Image Classification 6
Efficient Feature and Search Management for Real-Time Tracking 5
Robust Visual Tracking Under Appearance Variation 5
Asymmetric Spatiotemporal Decoupling for Video Models 4
Compressing Large Foundation Models via Knowledge Distillation 4
Reconstructing Complete Geometry from Partial Point Clouds 4
Test Time Adaptation for Distribution Shift 4
Conditioning Anomaly Detection on Scene Context 3
Stabilizing Medial Axis Transforms Against Boundary Noise 3
Diffeomorphic Flows for Topology Preserving Deformation 3
Composite Loss Functions for Perceptual Image Restoration 3

Top Authors

AuthorPapers
Luc Van Gool22
Mubarak Shah20
Ming-Hsuan Yang19
Nicu Sebe16
Kevin W. Bowyer15
Kyoung Mu Lee14
Rama Chellappa14
Alberto Del Bimbo13
Horst Bischof12
Rita Cucchiara12
Adrian Hilton11
In So Kweon11
Tinne Tuytelaars11
Vittorio Murino11
Haifeng Hu10
Cees G. M. Snoek9
Concetto Spampinato9
Edwin Hancock9
Sezer Karaoglu9
Theo Gevers9

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Mosaicing of camera-captured document images2009
Object separation by polarimetric and spectral imagery fusion2009
Object tracking using SIFT features and mean shift2009
Performance evaluation of local colour invariants2009
Probabilistic fusion-based parameter estimation for visual tracking2009
Pupil dilation degrades iris biometric performance2009
Robust feature point matching by preserving local geometric consistency2009
Search strategies for shape regularized active contour2009
Semi-supervised kernel density estimation for video annotation2009
Shape-from-recognition: Recognition enables meta-data transfer2009
Spatio-temporal constraints for on-line 3D object recognition in videos2009
Special issue on 3D representation for object and scene recognition2009
Surface reconstruction from point clouds by transforming the medial scaffold2009
Surround structured lighting: 3-D scanning with orthographic illumination2009
Unsupervised multiphase segmentation: A recursive approach2009
Unsupervised view and rate invariant clustering of video sequences2009
Video synchronization from human motion using rank constraints2009
Visual word proximity and linguistics for semantic video indexing and near-duplicate retrieval2009
A differential geometric approach to representing the human actions2008
Anytime similarity measures for faster alignment2008
Canonical subsets of image features2008
Change detection using a statistical model in an optimally selected color space2008
Combining visual dictionary, kernel-based similarity and learning strategy for image category retrieval2008
Content based video matching using spatiotemporal volumes2008
Discrete optimization in computer vision2008
Distinctive Similarity Measure for stereo matching under point ambiguity2008
Efficient belief propagation for higher-order cliques using linear constraint nodes2008
Efficient MRF deformation model for non-rigid image matching2008
HECOL: Homography and epipolar-based consistent labeling for outdoor park surveillance2008
ICA-based neighborhood preserving analysis for face recognition2008
Image understanding for iris biometrics: A survey2008
Improved spectral relaxation methods for binary quadratic optimization problems2008
Incremental and adaptive abnormal behaviour detection2008
Incremental, scalable tracking of objects inter camera2008
Limited view CT reconstruction and segmentation via constrained metric labeling2008
Locally adaptive subspace and similarity metric learning for visual data clustering and retrieval2008
Measuring novelty and redundancy with multiple modalities in cross-lingual broadcast news2008
Measuring uncertainty in graph cut solutions2008
Model-based human shape reconstruction from multiple views2008
Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views2008
Object recognition and segmentation in videos by connecting heterogeneous visual features2008
On geometric variational models for inpainting surface holes2008
Optimising dynamic graphical models for video content analysis2008
Performance vs computational efficiency for optimizing single and dynamic MRFs: Setting the state of the art with primal-dual strategies2008
Reducing drift in differential tracking2008
Registration of combined range-intensity scans: Initialization through verification2008
Retrieving multiple light sources in the presence of specular reflections and texture2008
Robust information clustering incorporating spatial information for breast mass detection in digitized mammograms2008
Robust object tracking with background-weighted local kernels2008
Shape matching and registration by data-driven EM2008

« prev Page 25/31 next »