Search Results for author:
Found 5 papers, 1 papers with code
Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
We evaluate over CATER dataset and find that Hopper achieves 73. 2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames.
Ranked #5 on
Video Object Tracking
on CATER
Supervised Feature Subset Selection and Feature Ranking for Multivariate Time Series without Feature Extraction
We introduce supervised feature ranking and feature subset selection algorithms for multivariate time series (MTS) classification.
On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
We revisit the classical analysis of generative vs discriminative models for general exponential families, and high-dimensional settings.
Controlling the Precision-Recall Tradeoff in Differential Dependency Network Analysis
We then show that by imposing a bias towards learning similar dependency networks for each condition the false discovery rates can be reduced to acceptable levels, at the cost of finding a reduced number of differences.
Bayesian models for Large-scale Hierarchical Classification
A challenging problem in hierarchical classification is to leverage the hierarchical relations among classes for improving classification performance.
