no code implementations • ICCV 2023 • Koutilya PNVR, Bharat Singh, Pallabi Ghosh, Behjat Siddiquie, David Jacobs
First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation.
no code implementations • CVPR 2021 • Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava
The standard paradigm is to utilize relationships in the input graph to transfer information using GCNs from training to testing nodes in the graph; for example, the semi-supervised, zero-shot, and few-shot learning setups.
no code implementations • 28 Aug 2020 • Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava
Current action recognition systems require large amounts of training data for recognizing an action.
Ranked #17 on Zero-Shot Action Recognition on Kinetics
no code implementations • 21 Jan 2020 • Pallabi Ghosh, Vibhav Vineet, Larry S. Davis, Abhinav Shrivastava, Sudipta Sinha, Neel Joshi
Given color images and noisy and incomplete target depth maps, we optimize a randomly-initialized CNN model to reconstruct a depth map restored by virtue of using the CNN network structure as a prior combined with a view-constrained photo-consistency loss.
no code implementations • 26 Nov 2018 • Pallabi Ghosh, Yi Yao, Larry S. Davis, Ajay Divakaran
We show results on CAD120 (which provides pre-computed node features and edge weights for fair performance comparison across algorithms) as well as a more complex real-world activity dataset, Charades.
1 code implementation • 27 Apr 2018 • Sohil Shah, Pallabi Ghosh, Larry S. Davis, Tom Goldstein
Many imaging tasks require global information about all pixels in an image.