Trep: Transformer-based evidential prediction for pedestrian intention with uncertainty
With rapid development in hardware (sensors and processors) and AI algorithms, automated
driving techniques have entered the public's daily life and achieved great success in …
driving techniques have entered the public's daily life and achieved great success in …
High dynamic range imaging with context-aware transformer
F Zhou, Z Fu, D Zhang - 2023 International Joint Conference on …, 2023 - ieeexplore.ieee.org
Avoiding the introduction of ghosts when synthesising LDR images as high dynamic range
(HDR) images is a challenging task. Convolutional neural networks (CNNs) are effective for …
(HDR) images is a challenging task. Convolutional neural networks (CNNs) are effective for …
Value functions factorization with latent state information sharing in decentralized multi-agent policy gradients
H Zhou, T Lan, V Aggarwal - IEEE Transactions on Emerging …, 2023 - ieeexplore.ieee.org
The use of centralized training and decentralized execution for value function factorization
demonstrates the potential for addressing cooperative multi-agent reinforcement tasks …
demonstrates the potential for addressing cooperative multi-agent reinforcement tasks …
A transfer learning framework for proactive ramp metering performance assessment
Transportation agencies need to assess ramp metering performance when deploying or
expanding a ramp metering system. The evaluation of a ramp metering strategy is primarily …
expanding a ramp metering system. The evaluation of a ramp metering strategy is primarily …
Traffic performance evaluation using statistical and machine learning methods
X Ma - 2022 - search.proquest.com
Fast and safe movement of people and goods is one of the key objectives of every efficient
transportation system. The rapid expansion of urbanization, economic growth, and the …
transportation system. The rapid expansion of urbanization, economic growth, and the …
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
Current techniques for deep neural network (DNN) pruning often involve intricate multi-step
processes that require domain-specific expertise making their widespread adoption …
processes that require domain-specific expertise making their widespread adoption …
Multi-task hierarchical adversarial inverse reinforcement learning
Abstract Multi-task Imitation Learning (MIL) aims to train a policy capable of performing a
distribution of tasks based on multi-task expert demonstrations, which is essential for …
distribution of tasks based on multi-task expert demonstrations, which is essential for …
[HTML][HTML] A computer vision-based automatic system for egg grading and defect detection
Simple Summary Egg defects such as cracks, dirty spots on the eggshell, and blood spots
inside the egg can decrease the quality and market value of table eggs. To address this …
inside the egg can decrease the quality and market value of table eggs. To address this …
Sampling through the lens of sequential decision making
Sampling is ubiquitous in machine learning methodologies. Due to the growth of large
datasets and model complexity, we want to learn and adapt the sampling process while …
datasets and model complexity, we want to learn and adapt the sampling process while …
On-ramp and Off-ramp Traffic Flows Estimation Based on A Data-driven Transfer Learning Framework
To develop the most appropriate control strategy and monitor, maintain, and evaluate the
traffic performance of the freeway weaving areas, state and local Departments of …
traffic performance of the freeway weaving areas, state and local Departments of …