Search Results for author:
Found 4 papers, 1 papers with code
Synthetic Dataset Creation and Fine-Tuning of Transformer Models for Question Answering in Serbian
In this paper, we focus on generating a synthetic question answering (QA) dataset using an adapted Translate-Align-Retrieve method.
Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking
We further propose a new cost function for associating observations with tracks.
Ranked #2 on
Multi-Object Tracking
on SportsMOT
(using extra training data)
Object Location Prediction in Real-time using LSTM Neural Network and Polynomial Regression
This represents a 76\% reduction in error compared to the traditional Kalman filter method, which has an average error of 0. 46 meters with a similar inference time to the LSTM-based system.
Intrinsically motivated option learning: a comparative study of recent methods
Options represent a framework for reasoning across multiple time scales in reinforcement learning (RL).
