A graph-based technique splits ambiguous instances into multiple points in DR projections to reduce partial neighborhood embedding and reveal hidden memberships.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.
MLLMs given the same instructions as human participants achieve expert-level performance on perceiving stress in network visualizations and rely on similar visual proxies.
Motion-based user identification works reliably inside one XR application but generalizes poorly across different applications.
Visualization retrieval systems can transform static collections of visualizations into dynamic, inquiry-based environments that support design exploration, data consumption, and resource management for data literacy education.
citing papers explorer
-
When One Point Is Not Enough: Addressing Ambiguous Instances in Dimensionality Reduction by Splitting
A graph-based technique splits ambiguous instances into multiple points in DR projections to reduce partial neighborhood embedding and reveal hidden memberships.
-
DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination
DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.
-
Exploring MLLMs Perception of Network Visualization Principles
MLLMs given the same instructions as human participants achieve expert-level performance on perceiving stress in network visualizations and rely on similar visual proxies.
-
Motion-Based User Identification across XR and Metaverse Applications by Deep Classification and Similarity Learning
Motion-based user identification works reliably inside one XR application but generalizes poorly across different applications.
-
Visualization Retrieval for Data Literacy: Position Paper
Visualization retrieval systems can transform static collections of visualizations into dynamic, inquiry-based environments that support design exploration, data consumption, and resource management for data literacy education.