Unsupervised video anomaly detection with self-attention based feature aggregating
Anomaly detection in surveillance videos is a crucial and challenging task in the intelligent
transportation systems. Previous methods utilize a memory module to store prototypical …
transportation systems. Previous methods utilize a memory module to store prototypical …
Pedestrian Simulation by Learning from Online Human Demonstration with VR Headset
F Yu, T Long, Z Cui, L Xu, L Li… - 2023 IEEE 26th …, 2023 - ieeexplore.ieee.org
Pedestrian simulation is essential for verifying the safety of autonomous vehicles in
simulators. The goal of pedes-trian simulation is to create realistic virtual representations of …
simulators. The goal of pedes-trian simulation is to create realistic virtual representations of …
Learning from Not All Vehicles via Influence Function
J Pang, T Long, Z Cui, L Xu, L Li… - 2023 IEEE 26th …, 2023 - ieeexplore.ieee.org
Learning robust driving policy for complex driving scenarios brings significant challenges to
autonomous driving system due to its inherent black-box properties. Recent methods learn …
autonomous driving system due to its inherent black-box properties. Recent methods learn …
Semantic Traffic Element Removal by Learning to Follow Linguistic Instructions
X Feng, Y Su, Y Liu, C Zhang - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
We propose a novel task of semantic object removal in traffic scenes through human-guided
image editing. Unlike traditional methods, our model does not require image masks; instead …
image editing. Unlike traditional methods, our model does not require image masks; instead …