PageRank Asymptotics on Directed Preferential Attachment Networks

no code implementations • 17 Feb 2021 • Sayan Banerjee, Mariana Olvera-Cravioto

We characterize the tail behavior of the distribution of the PageRank of a uniformly chosen vertex in a directed preferential attachment graph and show that it decays as a power law with an explicit exponent that is described in terms of the model parameters.

Probability Primary:05C80, Secondary: 60J80, 68P10, 41A60, 60B10

Directed Variational Cross-encoder Network for Few-shot Multi-image Co-segmentation

no code implementations • 17 Oct 2020 • Sayan Banerjee, S Divakar Bhat, Subhasis Chaudhuri, Rajbabu Velmurugan

Furthermore, the proposed framework does not use any semantic class labels and is entirely class agnostic.

Few-Shot Learning Segmentation +1

NENET: An Edge Learnable Network for Link Prediction in Scene Text

no code implementations • 25 May 2020 • Mayank Kumar Singh, Sayan Banerjee, Shubhasis Chaudhuri

Text detection in scenes based on deep neural networks have shown promising results.

Link Prediction regression +1

DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention

1 code implementation • 19 Feb 2020 • B. V. S Anusha, Sayan Banerjee, Subhasis Chaudhuri

These descriptors are extracted using DenseNet which significantly improves cross-sensor, cross-material and cross-dataset performance.