32 citations · 40 across the 4 of their papers we have counts for
4 papers
MPI-Flow: Learning Realistic Optical Flow with Multiplane Images
Yingping Liang, Jiaming Liu, Debing Zhang +1
The accuracy of learning-based optical flow estimation models heavily relies on the realism of the training datasets. Current approaches for generating such datasets either employ…
Recurrent Self-Supervised Video Denoising with Denser Receptive Field
Zichun Wang, Yulun Zhang, Debing Zhang +1
Self-supervised video denoising has seen decent progress through the use of blind spot networks. However, under their blind spot constraints, previous self-supervised video denoisi…
End-to-End Video Text Spotting with Transformer
Weijia Wu, Yuanqiang Cai, Chunhua Shen +4
Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post…
Partial FC: Training 10 Million Identities on a Single Machine
Xiang An, Xuhan Zhu, Yang Xiao +7
Training face recognition models with millions of identities is challenging because classifier storage, logit memory, and computation grow linearly with the number of classes, even…