no code implementations • 5 Jun 2021 • Sharmin Pathan, Vyom Shrivastava
In this paper, we present a novel approach to identify linked fraudulent activities or actors sharing similar attributes, using Graph Convolution Network (GCN).
no code implementations • 5 Jun 2021 • Sharmin Pathan, Vyom Shrivastava
Tasks and workers have time constraints and there is a cost associated with assigning a worker to a task.
no code implementations • 12 Apr 2020 • Sharmin Pathan, Anant Tripathi
We use the deep clustering branch for clustering images into four clusters.
no code implementations • 31 Jul 2019 • Sharmin Pathan
Later this object specific information gets appended to the room attributes (room_type, room_size, preferred_tone, etc) and a deep neural net is trained to make predictions for color/texture/wallpaper for the walls.
no code implementations • 19 Aug 2018 • Sharmin Pathan, Yi Hong
Features extracted by the LSTM and CNN are fed into a decoder network to reconstruct the vector momentum sequence, which is used for the image sequence prediction by deforming the baseline image with LDDMM shooting.