Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection
In frame-based vision, object detection faces substantial performance degradation under
challenging conditions due to the limited sensing capability of conventional cameras. Event …
challenging conditions due to the limited sensing capability of conventional cameras. Event …
A progressive segmentation network for navigable areas with semantic-spatial information flow
Segmentation of safe navigable areas is a crucial technology for scene parsing in autopilot
systems. However, existing segmentation methods often fail to adequately exploit the …
systems. However, existing segmentation methods often fail to adequately exploit the …
Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition
Existing event stream-based pattern recognition models usually represent the event stream
as the point cloud, voxel, image, etc., and design various deep neural networks to learn their …
as the point cloud, voxel, image, etc., and design various deep neural networks to learn their …
[PDF][PDF] Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection–Supplementary Material
DDD17. The vehicles in the DDD17 dataset were manually labeled by the authors of [11] to
create the PKU-DDD17-Car dataset for object detection tasks. Additional details about the …
create the PKU-DDD17-Car dataset for object detection tasks. Additional details about the …