Search Results for author:
Found 6 papers, 3 papers with code
Multi-Object Tracking as Attention Mechanism
We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks.
Toward Asymptotic Optimality: Sequential Unsupervised Regression of Density Ratio for Early Classification
Theoretically-inspired sequential density ratio estimation (SDRE) algorithms are proposed for the early classification of time series.
Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis
As a result, we obtain EoM, a continuous differential equation that precisely describes the discrete learning dynamics of GD.
Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series
To resolve this tradeoff, we propose Adaptive Multi-scale Pooling, which aggregates features from an adaptive number of layers, i. e., only the first few layers for short data and more layers for long data.
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
We propose a model for multiclass classification of time series to make a prediction as early and as accurate as possible.
Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high.
