DSNet uses cascaded dense dilated convolution blocks with a multi-scale density level consistency loss to report state-of-the-art results on four standard crowd counting datasets.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
MTS-DR-Net introduces MTS layers and MTS-DR blocks as a backbone for edge detection followed by a weighted U-shaped refinement module, evaluated on BSDS500 and BIPEDv2 datasets.
A joint end-to-end learning method for multi-view object instance detection and re-identification that incorporates learned geometric soft constraints, validated on a new street-level panorama dataset.
CovNorm reduces parameters in domain-adaptive layers via two PCAs and a mini-adaptation layer, enabling efficient multi-domain learning with performance close to full fine-tuning.
citing papers explorer
-
Dense Scale Network for Crowd Counting
DSNet uses cascaded dense dilated convolution blocks with a multi-scale density level consistency loss to report state-of-the-art results on four standard crowd counting datasets.
-
Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection
MTS-DR-Net introduces MTS layers and MTS-DR blocks as a backbone for edge detection followed by a weighted U-shaped refinement module, evaluated on BSDS500 and BIPEDv2 datasets.
-
Simultaneous multi-view instance detection with learned geometric soft-constraints
A joint end-to-end learning method for multi-view object instance detection and re-identification that incorporates learned geometric soft constraints, validated on a new street-level panorama dataset.
-
Efficient Multi-Domain Network Learning by Covariance Normalization
CovNorm reduces parameters in domain-adaptive layers via two PCAs and a mini-adaptation layer, enabling efficient multi-domain learning with performance close to full fine-tuning.