Search Results for author: Deepak Srivatsav

Found 2 papers, 1 papers with code

COBRA: Contrastive Bi-Modal Representation Algorithm

1 code implementation7 May 2020 Vishaal Udandarao, Abhishek Maiti, Deepak Srivatsav, Suryatej Reddy Vyalla, Yifang Yin, Rajiv Ratn Shah

In this paper, we present a novel framework COBRA that aims to train two modalities (image and text) in a joint fashion inspired by the Contrastive Predictive Coding (CPC) and Noise Contrastive Estimation (NCE) paradigms which preserve both inter and intra-class relationships.

Cross-Modal Retrieval Image Captioning +3

Attentional Road Safety Networks

no code implementations12 Dec 2018 Sonu Gupta, Deepak Srivatsav, A. V. Subramanyam, Ponnurangam Kumaraguru

Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning.

Domain Adaptation

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