ECCV 2022

1,670 papers

Top Research Directions

Research directions most represented by ECCV 2022 papers.

Generalizing from Synthetic Data to the Real World 30
Exploiting Temporal Redundancy in Video Neural Networks 23
Addressing Inductive Bias Deficiency in Vision Transformers 21
Cross Task Generalization in Image Restoration 18
Scaling Visual Attention Beyond Quadratic Complexity 18
Preserving Tiny Features Against Spatial Resolution Degradation 16
Decoupled Spatiotemporal Attention in Transformer Architectures 15
Cascaded Error Propagation in 2D to 3D Lifting 14
Mitigating Error Propagation in Pseudo Labeling 14
Bypassing the Computational Bottleneck of Adversarial Training 14
Disentangling Attribute Control in Generative Models 13
Overcoming Local Receptive Field Constraints in Visual Models 13
Deep Learning on Unstructured 3D Point Clouds 13
Clean Accuracy Degradation in Machine Learning Defenses 13
Dense Prediction Adaptation 12

Top Authors

AuthorPapers
Giovanni Maria Farinella26
Dacheng Tao15
Luc Van Gool14
Ziwei Liu13
Chen Change Loy12
Alan Yuille10
Jing Zhang10
Rongrong Ji10
Shouhong Ding10
Yu Qiao10
Hongsheng Li9
Xiang Bai9
Boxin Shi8
Nicu Sebe8
Shuicheng YAN8
Wanli Ouyang8
Xiatian Zhu8
Zhangyang Wang8
Zhe Lin8
Errui Ding7

Impactful Papers

Papers from ECCV 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Tomography of Turbulence Strength Based on Scintillation Imaging
TO-Scene: A Large-Scale Dataset for Understanding 3D Tabletop Scenes
Totems: Physical Objects for Verifying Visual Integrity
Towards Accurate Active Camera Localization
Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies
Towards Accurate Network Quantization with Equivalent Smooth Regularizer
Towards Accurate Open-Set Recognition via Background-Class Regularization
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning
Towards Comprehensive Representation Enhancement in Semantics-Guided Self-supervised Monocular Depth Estimation
Towards Data-Efficient Detection Transformers
Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Towards Efficient Adversarial Training on Vision Transformers
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing
Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline
Towards Grand Unification of Object Tracking
Towards Hard-Positive Query Mining for DETR-Based Human-Object Interaction Detection
Towards High-Fidelity Single-View Holistic Reconstruction of Indoor Scenes
Towards Interpretable Video Super-Resolution via Alternating Optimization
Towards Learning Neural Representations from Shadows
Towards Metrical Reconstruction of Human Faces
Towards Open Set Video Anomaly Detection
Towards Open-Vocabulary Scene Graph Generation with Prompt-Based Finetuning
Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation
Towards Realistic Semi-supervised Learning
Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach
Towards Regression-Free Neural Networks for Diverse Compute Platforms
Towards Robust Face Recognition with Comprehensive Search
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Towards Sequence-Level Training for Visual Tracking
Towards Ultra Low Latency Spiking Neural Networks for Vision and Sequential Tasks Using Temporal Pruning
Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian
Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
Trace Controlled Text to Image Generation
Tracking by Associating Clips
Tracking Every Thing in the Wild
Tracking Objects as Pixel-Wise Distributions
Trading Positional Complexity vs Deepness in Coordinate Networks
Trading Positional Complexity vs. Deepness in Coordinate Networks
Training Vision Transformers with only 2040 Images
Transfer Without Forgetting
TransFGU: A Top-Down Approach to Fine-Grained Unsupervised Semantic Segmentation
Transformers as Meta-learners for Implicit Neural Representations
Transformer with Implicit Edges for Particle-Based Physics Simulation
Transform Your Smartphone into a DSLR Camera: Learning the ISP in the Wild
TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance
Translating a Visual LEGO Manual to a Machine-Executable Plan
Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection
TransMatting: Enhancing Transparent Objects Matting with Transformers
TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning

« prev Page 31/34 next »