14 citations · 19 across the 4 of their papers we have counts for
4 papers
Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video
Pu Li, Xiaobai Liu
This paper presents an unsupervised approach that leverages raw aerial videos to learn to estimate planar homographic transformation between consecutive video frames. Previous lear…
Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrograms
Pu Li, Marie Roch, Holger Klinck +5
Whistle contour extraction aims to derive animal whistles from time-frequency spectrograms as polylines. For toothed whales, whistle extraction results can serve as the basis for a…
SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations
Pu Li, Jianwei Guo, Xiaopeng Zhang +1
Reverse engineering CAD models from raw geometry is a classic but strenuous research problem. Previous learning-based methods rely heavily on labels due to the supervised design pa…
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours
Pu Li, Xiaobai Liua, K. J. Palmer +8
We present a learning-based method for extracting whistles of toothed whales (Odontoceti) in hydrophone recordings. Our method represents audio signals as time-frequency spectrogra…