Synthetic RAW augmentations create continuous low-light samples matching sensor noise, enabling fine-grained evaluation of person detection performance where real data is sparse.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
A lightweight segmentation network learns associative embeddings to assign consistent descriptors to unconnected pixels of same-team players for game-agnostic team discrimination in basketball videos.
Knowledge distillation from a rigid-invariant 3D point cloud network into a regulated multi-view Transformer yields lower-error, faster wheat spike volume estimates from 2D images.
citing papers explorer
-
Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
Synthetic RAW augmentations create continuous low-light samples matching sensor noise, enabling fine-grained evaluation of person detection performance where real data is sparse.
-
Associative Embedding for Game-Agnostic Team Discrimination
A lightweight segmentation network learns associative embeddings to assign consistent descriptors to unconnected pixels of same-team players for game-agnostic team discrimination in basketball videos.
-
3D Reconstruction and Knowledge Distillation to Improve Multi-View Image Models to Explore Spike Volume Estimation in Wheat
Knowledge distillation from a rigid-invariant 3D point cloud network into a regulated multi-view Transformer yields lower-error, faster wheat spike volume estimates from 2D images.