3260 papers • 126 benchmarks • 313 datasets
Image: Choy et al
(Image credit: Papersgraph)
These leaderboards are used to track progress in 4d-spatio-temporal-semantic-segmentation-19
No benchmarks available.
Use these libraries to find 4d-spatio-temporal-semantic-segmentation-19 models and implementations
No datasets available.
No subtasks available.
This work creates an open-source auto-differentiation library for sparse tensors that provides extensive functions for high-dimensional convolutional neural networks and proposes the hybrid kernel, a special case of the generalized sparse convolution, and trilateral-stationary conditional random fields that enforce spatio-temporal consistency in the 7D space-time-chroma space.
Proposed CNN based segmentation approaches demonstrate how 2D segmentation using prior slices can provide similar results to 3D segmentations while maintaining good continuity in the 3D dimension and improved speed.
Adding a benchmark result helps the community track progress.