GSHAC performs exact HAC on large geographic point sets by building a sparse geodesic graph and proving that connected-component subproblems yield identical results to the dense algorithm for all standard linkages at cut heights below the sparsity threshold.
A transformer-based framework for multivariate time series representation learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.
Transformer models classify seven wildlife species from daily GPS trajectories, outperforming LSTM, CNN, and TCN baselines by 8-22 percentage points in balanced accuracy under region-holdout evaluation.
citing papers explorer
-
Scalable Exact Hierarchical Agglomerative Clustering via Sparse Geographic Distance Graphs
GSHAC performs exact HAC on large geographic point sets by building a sparse geodesic graph and proving that connected-component subproblems yield identical results to the dense algorithm for all standard linkages at cut heights below the sparsity threshold.
-
Rotary Masked Autoencoders are Versatile Learners
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.
-
Transformer-Based Wildlife Species Classification from Daily Movement Trajectories
Transformer models classify seven wildlife species from daily GPS trajectories, outperforming LSTM, CNN, and TCN baselines by 8-22 percentage points in balanced accuracy under region-holdout evaluation.