ICPR 2022
303 papers
The 2022 edition of the International Conference on Pattern Recognition (ICPR) featured 388 papers covering a broad spectrum of computer vision and machine learning topics. Key research directions included trajectory prediction using differentiable geometric constraints, learning safety boundaries for robotics, and discovering novel categories without predefined cluster counts. There was a focus on improving model robustness through automated shortcut discovery, counterfactual data augmentation, and selective consistency regularization for domain generalization.
Methodological trends highlighted the integration of self-supervision with semi-supervised learning and the use of geometric self-supervision for semantic understanding. Specific applications explored during this edition included weather-aware object detection, cloth-changing person re-identification, and lightweight architectures for remote sensing land-cover classification. Prolific contributors to the proceedings included Xiaohua Xie, Jing Dong, Wei Wang, and Rita Cucchiara. The research collectively addressed challenges in out-of-distribution detection, low-rank matrix recovery, and probabilistic label aggregation for noisy datasets.
Top Research Directions
Research directions most represented by ICPR 2022 papers.
Top Authors
Impactful Papers
Papers from ICPR 2022 that shaped research clusters.
Foundational
Unsupervised Domain Adaptation for Video Transformers in Action Recognition
foundational
Inherent Robustness of Vision Transforme
Influential
Effects of Auxiliary Knowledge on Continual Learning
influential
Knowledge Retention in Continual Deep Le
Visual Transformers with Primal Object Queries for Multi-Label Image Classification
influential
Mixup Regularization via Linear Sample I
VPTR: Efficient Transformers for Video Prediction
influential
Modeling Multimodal Uncertainty in Video
Extremely Low-Light Image Enhancement with Scene Text Restoration
influential
Restoring Visual Structure in Low Light
3D-NVS: A 3D Supervision Approach for Next View Selection
influential
Synthetic Viewpoint Augmentation for Rob
Forecasting of depth and ego-motion with transformers and self-supervision
influential
Edge Aware Depth Regularization
Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes
influential
Transfer Learning via Fixed Feature Extr
MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator
influential
Mitigating Long Range Sparsity in 3D Obj
Dynamic Data Augmentation with Gating Networks for Time Series Recognition
influential
Dynamic Data Augmentation Scheduling
3D-NVS: A 3D Supervision Approach for Next View Selection
influential
Active Viewpoint Selection for 3D Recons