Synthesis 2022

111 papers
Synthesis 2022 featured 125 papers covering diverse computational topics, with a significant emphasis on acoustic simulation and domain adaptation. Research in sound propagation explored hybrid wave-geometric methods and neural acoustic fields to achieve realistic spatial audio. Parallel to this, a substantial body of work addressed challenges in machine learning robustness, specifically focusing on dataset bias, domain shift, and unsupervised domain adaptation through entropy minimization and adversarial alignment. The edition also highlighted advancements in graph-based learning, including applications for fashion compatibility modeling and personalized online content management. Notable contributions explored fundamental graph neural networks and network connectivity optimization. Prolific contributors to the 2022 proceedings included researchers such as Rishiraj Saha Roy, Aidan Hogan, and Axel Polleres. The collective work reflects a trend toward integrating physics-based synthesis with neural methods and refining model performance across heterogeneous data environments through techniques like domain-specific batch normalization.

Top Research Directions

Research directions most represented by Synthesis 2022 papers.

The Definitional Challenge of Network Communities 1
Explaining AI Decisions Through Model Reconciliation 1
Hybrid Geometric and Wave Acoustic Simulation 1
Domain Specific Normalization for Multi Source Learning 1
Anticipatory Control for Proactive Human Robot Collaboration 1
Cascading Failures in Interdependent Networks 1
The Temporal Dynamics of Human AI Trust 1
Adversarial Training for Domain Invariant Representations 1
Preventing Negative Transfer from Outlier Class Interference 1
The Perceptual Evaluation Gap in Generative Audio 1
Domain Adaptation with Category Shift 1
Incremental Maintenance of Dynamic Graph Indices 1
Adapting Deep Networks to Distribution Shift 1
Source Free Domain Adaptation 1

Top Authors

AuthorPapers
Michael Cochez12
Steffen Staab12
Tiago Novello10
Liqiang Nie8
Xuemeng Song8
Andrew Yates7
Dinesh Manocha7
Francesco Bonchi7
Hanghang Tong7
Chen Chen6
Gang Chen3
Cheng Yang2
Chuan Shi2
Xiao Wang2
Bing He1
Deyu Bo1
Jimmy Lin1
Yaoqi Liu1

Impactful Papers

Papers from Synthesis 2022 that shaped research clusters.

Influential

Papers

Title
Sound Synthesis
Sound Synthesis, Propagation, and Rendering
Summary and Discussion
Supervised Disentangled Graph Learning for OCM
The Case of A Single Server
The General Case of Multiple Servers
Theoretical Background
Traditional Methods
Unsupervised Disentangled Graph Learning for OCM
Visual Domain Adaptation in the Deep Learning Era
Visualization of Three-Dimensional Spaces

« prev Page 3/3