Search Results for author: Skand Vishwanath Peri

Found 5 papers, 4 papers with code

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

3 code implementations ICLR 2020 Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn

Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes.

Representation Learning

Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet)

1 code implementation31 Jul 2018 Jatin Garg, Skand Vishwanath Peri, Himanshu Tolani, Narayanan C. Krishnan

Further, recognizing the identity in the image by knowledge transfer using a combination of shared and modality specific representations, resulted in an unprecedented performance of 85% rank-1 accuracy for caricatures and 95% rank-1 accuracy for visual images.

Caricature Face Recognition +2

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classification

no code implementations26 Jul 2018 Apoorva Sikka, Skand Vishwanath Peri, Deepti. R. Bathula

The accuracy using only MRI is 70. 18% while joint classification using synthesized PET and MRI is 74. 43% with a p-value of $0. 06$.

General Classification SSIM

Cannot find the paper you are looking for? You can Submit a new open access paper.