Search Results for author:
Found 5 papers, 2 papers with code
DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification
In occluded person re-identification(ReID), severe occlusions lead to a significant amount of irrelevant information that hinders the accurate identification of individuals.
A new baseline for edge detection: Make Encoder-Decoder great again
Our study shows that what really matters in the current edge detection is high-quality features, and we can make the encoder-decoder based detector great again even without complex training strategies and huge computational cost.
Compact Twice Fusion Network for Edge Detection
In this work, we propose a Compact Twice Fusion Network (CTFN) to fully integrate multi-scale features while maintaining the compactness of the model.
Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders
Scale-space representation has been popular in computer vision community due to its theoretical foundation.
Unsupervised domain adaption dictionary learning for visual recognition
However, when the data instances of a target domain have a different distribution than that of a source domain, the dictionary learning method may fail to perform well.
