Unsupervised EM-based joint optimization of interest point detector and descriptor via probability formulations of sparsity, repeatability and discriminability, yielding Property Network that outperforms SOTA on matching benchmarks without retraining.
Fully convolutional networks for semantic segmentation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
AVD maps videos to semantically realistic 2D images via 3D conv encoder-decoder plus adversarial training, enabling image-based classifiers to perform video activity recognition.
citing papers explorer
-
Unsupervised Learning Framework of Interest Point Via Properties Optimization
Unsupervised EM-based joint optimization of interest point detector and descriptor via probability formulations of sparsity, repeatability and discriminability, yielding Property Network that outperforms SOTA on matching benchmarks without retraining.
-
AVD: Adversarial Video Distillation
AVD maps videos to semantically realistic 2D images via 3D conv encoder-decoder plus adversarial training, enabling image-based classifiers to perform video activity recognition.