IJCV

2,833 papers1,709 directions
The International Journal of Computer Vision 2019 serves as a venue for research in computer vision and machine learning, publishing 33 papers during this period. The venue focuses on the evolution of visual recognition techniques, documenting the transition from traditional methods like Bag-of-Words to modern convolutional neural networks. Its content covers a broad range of technical domains, including texture classification, spatio-temporal reasoning for video question answering, and weakly supervised object detection frameworks. Research at this venue also emphasizes practical applications in facial recognition and image segmentation. Specific studies address face-specific data augmentation for unconstrained environments and large-scale learning for identification tasks. Furthermore, the venue includes work on human-in-the-loop systems, such as interactive object segmentation through point clicks and methods for distributing workloads between human annotators and automated algorithms. The contributions involve several researchers in the field, such as Rama Chellappa, Kristen Grauman, and Maja Pantic. By presenting research on collaborative self-paced curriculum learning and visual question answering, the venue facilitates the exchange of ideas regarding how prior knowledge and multiple cues can improve model performance. The collected works reflect the state of computer vision research in 2019, focusing on improving the robustness and efficiency of visual processing systems.

Papers by Year

2026 287
2025 372
2024 309
2023 189
2022 171
2021 168
2020 159
2019 119
2018 95
2017 105
2016 107
2015 100
2014 107
2013 84
2012 91
2011 51
2010 50
2009 69
2008 57
2007 45
2006 50
2005 30
2004 38
2003 21
2002 29
2001 18
2000 32
1999 23
1998 22
1997 21
1996 18
1995 25
1994 6
1993 6
1992 6
1991 1
1990 8
1989 1
1988 5
1987 2

Top Research Directions

Research directions most represented by papers from this venue.

Generalizing from Synthetic Data to the Real World 15
Test Time Adaptation for Distribution Shift 13
Preserving Tiny Features Against Spatial Resolution Degradation 12
Deep Learning on Unstructured 3D Point Clouds 9
The Cross Modal Representation Gap 8
Resolving Kinematic Ambiguity in Skeleton Based Action Recognition 7
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 7
Mitigating Identity Switches under High Visual Similarity 7
3D Convolutions for Spatiotemporal Feature Learning 7
Hierarchical Feature Fusion across Network Depths 7
Object Detection via Center Point Heatmaps 6
Spectral Functional Maps for Geometric Alignment 6
Concept Based Explanations for Deep Learning Models 6
Identity Preserving Feature Losses for Face Manipulation 6
Generalizing to Unseen Categories via Shared Semantic Spaces 6

Top Authors

AuthorPapers
Luc Van Gool52
Dacheng Tao43
Andrew Zisserman35
Chunhua Shen33
Ming-Hsuan Yang32
Cordelia Schmid24
Kristen Grauman24
Rama Chellappa24
Stephen Maybank23
Jean Ponce21
Richard Hartley20
Bernt Schiele19
Chen Change Loy19
Ron Kimmel19
Tao Xiang19
Jingdong Wang18
Marc Pollefeys18
Nicu Sebe18
Shuicheng YAN18
Daniel Cremers17

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Spatial Color Indexing and Applications1999
Stereo Matching with Transparency and Matting1999
Structure and Motion Estimation from Dynamic Silhouettes under Perspective Projection1999
Temporal Multi-Scale Models for Flow and Acceleration1999
The Bas-Relief Ambiguity1999
Theory and Practice of Projective Rectification1999
The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences1999
The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences.1999
Topographic Maps and Local Contrast Changes in Natural Images1999
Visual Homing: Surfing on the Epipoles1999
Volumetric Deformation Analysis Using Mechanics-Based Data Fusion: Applications in Cardiac Motion Recovery1999
When is it Possible to Identify 3D Objects From Single Images Using Class Constraints?1999
Ambiguity in Structure from Motion: Sphere versus Plane1998
Chirality1998
Differential and Numerically Invariant Signature Curves Applied to Object Recognition1998
Directions of Motion Fields are Hardly Ever Ambiguous1998
Dual Computation of Projective Shape and Camera Positions from Multiple Images1998
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation1998
Epipolar Geometry and Linear Subspace Methods: A New Approach to Weak Calibration1998
Extracting Salient Curves from Images: An Analysis of the Saliency Network1998
Fast, Accurate and Consistent Modeling of Drainage and Surrounding Terrain1998
Feature Detection with Automatic Scale Selection1998
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling1998
Generalization to Novel Views: Universal, Class-based, and Model-based Processing1998
Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes1998
New Geometric Methods for Computer Vision: An Application to Structure and Motion Estimation1998
Rapid Anisotropic Diffusion Using Space-Variant Vision1998
Reliable and Efficient Computation of Optical Flow1998
Robust Algorithms for Object Localization1998
Robust Shape Recovery from Occluding Contours Using a Linear Smoother1998
Stereo Matching with Nonlinear Diffusion1998
Temporal Analysis of Motion in Video Sequences through Predictive Operators1998
Transfer of Fixation Using Affine Structure: Extending the Analysis to Stereo1998
Uncertainty Propagation in Model-Based Recognition1998
3-D Scene Data Recovery Using Omnidirectional Multibaseline Stereo1997
A General Motion Model and Spatio-Temporal Filters for Computing Optical Flow1997
Alignment by Maximization of Mutual Information1997
Computing Local Surface Orientation and Shape from Texture for Curved Surfaces1997
From Multiple Stereo Views to Multiple 3-D Surfaces1997
Geodesic Active Contours1997
Global Minimum for Active Contour Models: A Minimal Path Approach1997
Learning Recognition and Segmentation Using the Cresceptron1997
Lines and Points in Three Views and the Trifocal Tensor1997
Matching 3-D Models to 2-D Images1997
On Photometric Issues in 3D Visual Recognition from a Single 2D Image1997
On the Geometry of Visual Correspondence1997
Recognition Using Region Correspondences1997
Recursive 3-D Visual Motion Estimation Using Subspace Constraints1997
Self-Calibration of Stationary Cameras1997
Sequential Updating of Projective and Affine Structure from Motion1997

« prev Page 55/57 next »