ICCV

11,370 papers6,704 directions

Papers by Year

2026 30
2025 2,139
2024 20
2023 2,233
2022 157
2021 1,624
2020 87
2019 1,184
2018 49
2017 628
2016 6
2015 530
2014 3
2013 458
2011 339
2009 315
2007 398
2006 1
2005 258
2003 199
2002 1
2001 221
1999 176
1998 166
1995 162
1993 102
1990 127
1988 89

Top Research Directions

Research directions most represented by papers from this venue.

Generalizing from Synthetic Data to the Real World 125
Efficient Training and Inference for Diffusion Models 83
Preserving Tiny Features Against Spatial Resolution Degradation 77
Mitigating Error Propagation in Pseudo Labeling 68
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 66
The Sensitivity of Multi-Objective Loss Balancing 66
Reconstructing Complete Geometry from Partial Point Clouds 65
Deep Learning on Unstructured 3D Point Clouds 62
Resolving Depth Ambiguity in Monocular 3D Reconstruction 61
Overcoming the Static Scene Assumption 60
Exploiting Temporal Redundancy in Video Neural Networks 60
Overcoming Local Receptive Field Constraints in Visual Models 59
Asymmetric Spatiotemporal Decoupling for Video Models 57
Geometric Degeneracy in Camera Pose Estimation 56
Eliminating the Optical Flow Bottleneck in Video Understanding 55

Top Authors

AuthorPapers
Luc Van Gool90
Marc Pollefeys60
Shuicheng YAN60
Cordelia Schmid52
Andrew Zisserman51
Mubarak Shah47
Jiaya Jia46
Song-Chun Zhu46
Jitendra Malik45
Daniel Cremers43
Ming-Hsuan Yang43
Alan Yuille38
Ling Shao38
Hongsheng Li36
Wanli Ouyang36
Yi Yang36
Antonio Torralba35
Chen Change Loy35
Chunhua Shen34
Huchuan Lu32

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Single image super-resolution via deep learning2022
Single-pixel imaging encryption based on 2D coupled Logistic mapping2022
Sitting Posture Detection System Based on Keras Framework2022
SOLOv2-cable: A Power Cable Segmentation Algorithm in Complex Scenarios2022
Spare parts consumption prediction based on AO-ELM2022
Testing the feasibility of quantizing the progress of stroke patients’ rehabilitation with a computer vision method2022
2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 20212021
3D Building Reconstruction from Monocular Remote Sensing Images2021
3DeepCT: Learning Volumetric Scattering Tomography of Clouds2021
3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics2021
3D Human Pose Estimation with Spatial and Temporal Transformers2021
3D Human Texture Estimation from a Single Image with Transformers2021
3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces2021
3D Local Convolutional Neural Networks for Gait Recognition2021
3D Shape Generation and Completion through Point-Voxel Diffusion2021
3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations2021
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds2021
4D Cloud Scattering Tomography2021
4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface2021
4D-Net for Learned Multi-Modal Alignment2021
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network2021
A Backdoor Attack against 3D Point Cloud Classifiers2021
A Broad Study on the Transferability of Visual Representations with Contrastive Learning2021
ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning2021
Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform2021
ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding2021
ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot2021
Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search2021
A Closer Look at Rotation-invariant Deep Point Cloud Analysis2021
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo2021
Action-Conditioned 3D Human Motion Synthesis with Transformer VAE2021
Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings2021
Active Learning for Deep Object Detection via Probabilistic Modeling2021
Active Learning for Lane Detection: A Knowledge Distillation Approach2021
Active Universal Domain Adaptation2021
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery2021
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer2021
AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds2021
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition2021
Adaptive Adversarial Network for Source-free Domain Adaptation2021
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection2021
Adaptive confidence thresholding for monocular depth estimation2021
Adaptive Convolutions with Per-pixel Dynamic Filter Atom2021
Adaptive Curriculum Learning2021
Adaptive Focus for Efficient Video Recognition2021
Adaptive Graph Convolution for Point Cloud Analysis2021
Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference2021
Adaptive Label Noise Cleaning with Meta-Supervision for Deep Face Recognition2021
Adaptive Surface Normal Constraint for Depth Estimation2021
Adaptive Surface Reconstruction with Multiscale Convolutional Kernels2021

« prev Page 89/228 next »