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
MoFaNeRF: Morphable Facial Neural Radiance Field
Monitored Distillation for Positive Congruent Depth Completion
Monocular 3D Object Detection with Depth from Motion
Monocular 3D Object Reconstruction with GAN Inversion
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene Flow Estimation with Monocular Images
MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
Most and Least Retrievable Images in Visual-Language Query Systems
MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Motion and Appearance Adaptation for Cross-domain Motion Transfer
MotionCLIP: Exposing Human Motion Generation to CLIP Space
Motion Sensitive Contrastive Learning for Self-supervised Video Representation
Motion Transformer for Unsupervised Image Animation
MOTR: End-to-End Multiple-Object Tracking with Transformer
MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning
MTTrans: Cross-domain Object Detection with Mean Teacher Transformer
MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
Multi-Curve Translator for High-Resolution Photorealistic Image Translation
Multi-domain Learning for Updating Face Anti-spoofing Models
Multi-domain Multi-definition Landmark Localization for Small Datasets
Multi-Exit Semantic Segmentation Networks
Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection
Multi-granularity Distillation Scheme Towards Lightweight Semi-supervised Semantic Segmentation
Multi-granularity Prediction for Scene Text Recognition
Multi-granularity Pruning for Model Acceleration on Mobile Devices
MultiMAE: Multi-modal Multi-task Masked Autoencoders
Multimodal Conditional Image Synthesis with Product-of-Experts GANs
Multimodal Object Detection via Probabilistic Ensembling
Multi-modal Text Recognition Networks: Interactive Enhancements Between Visual and Semantic Features
Multimodal Transformer for Automatic 3D Annotation and Object Detection
Multimodal Transformer with Variable-Length Memory for Vision-and-Language Navigation
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
Multi-query Video Retrieval
Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation
Multiview Regenerative Morphing with Dual Flows
Multiview Stereo with Cascaded Epipolar RAFT
MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution
Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection
MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
MVDG: A Unified Multi-view Framework for Domain Generalization
MVP: Multimodality-Guided Visual Pre-training
MVSalNet: Multi-view Augmentation for RGB-D Salient Object Detection
MVSTER: Epipolar Transformer for Efficient Multi-view Stereo
My View is the Best View: Procedure Learning from Egocentric Videos
NashAE: Disentangling Representations Through Adversarial Covariance Minimization
Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization

« prev Page 20/34 next »