ICPR 2020
695 papers
The 2020 edition of the International Conference on Pattern Recognition (ICPR) included 942 papers, with a strong emphasis on multimodal learning and representation. Research directions involved multimodal feature fusion, fine-grained alignment, and prediction for autonomous agents. Notable attention was given to bridging the domain gap for synthetic training data and mitigating shortcut learning in self-supervised models. Methodological trends included the exploration of neural collapse, geometric feature packing, and permutation invariance in 3D point cloud learning.
Technical contributions also addressed neural architecture search for embedded systems and knowledge distillation through automatic student network search. In terms of applications, the proceedings featured work on brain network encoding for disease classification, semi-supervised person re-identification, and image-to-latex conversion using Transformer models. Prolific authors contributing to this year’s research included Rita Cucchiara, Ran He, Simone Calderara, and Edwin R. Hancock. The research collectively focused on improving model robustness against label noise and optimizing cyclic consistency for image-to-image translation.
Top Research Directions
Research directions most represented by ICPR 2020 papers.
Top Authors
Impactful Papers
Papers from ICPR 2020 that shaped research clusters.
Foundational
On the Information of Feature Maps and Pruning of Deep Neural Networks
foundational
Non-Monotonic Information Flow in Deep N
Picture-to-Amount (PITA): Predicting Relative Ingredient Amounts from Food Images
foundational
Quantitative Ingredient Estimation for N
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classi
foundational
Simplex Structured Latent Spaces
$P^{2}$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
foundational
Learning Data Augmentation through Gradi
CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
foundational
Pseudo-Label Guided Adversarial Training
Offset Curves Loss for Imbalanced Problem in Medical Segmentation
foundational
Hybrid Region and Boundary Loss for Imag
ESResNet: Environmental Sound Classification Based on Visual Domain Models
foundational
Joint Time-Frequency Attention for Acous
Let's Play Music: Audio-Driven Performance Video Generation
foundational
Decoupling Camera and Object Motion in V
Future Urban Scenes Generation Through Vehicles Synthesis
foundational
Temporal Drift in Long-Horizon Video Gen
Semantic-Guided Inpainting Network for Complex Urban Scenes Manipulation
foundational
Spatially Adaptive Normalization for Con
Influential
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classi
influential
Maximizing Class Separation for Adversar
AttendAffectNet: Self-Attention based Networks for Predicting Affective Responses from Movies
influential
Concordance Correlation Loss for Continu
CKG: Dynamic Representation Based on Context and Knowledge Graph
influential
Contextual Disambiguation of Polysemous
Detective: An Attentive Recurrent Model for Sparse Object Detection
influential
Eliminating Region Proposal Redundancy i
Predicting Online Video Advertising Effects with Multimodal Deep Learning
influential
Dynamic Modality Weighting for Multimoda
On the Information of Feature Maps and Pruning of Deep Neural Networks
influential
Iterative Structural Pruning for Neural
CKG: Dynamic Representation Based on Context and Knowledge Graph
influential
The Incompleteness Bottleneck of Externa
T-SVD Based Non-convex Tensor Completion and Robust Principal Component Analysis
influential
Non-convex Rank Approximation for Multid
Progressive Learning Algorithm for Efficient Person Re-Identification
influential
Automated Hyperparameter Tuning via Baye
Papers
« prev Page 14/14