Arijit Ray

TL;DR: In this article, a new model for the metasomatism and rifting of the Kutch lithosphere, and magma generation from a CO2-rich lherzolite mantle was presented.

TL;DR: This work measures the size-magnetic field evolution, baryon loading and energetics, using the observed radio spectra of SN 2009bb to establish that engine-driven SNe can readily explain the post-GZK UHECRs.

TL;DR: A dataset, ConVQA, and metrics that enable quantitative evaluation of consistency in VQA are introduced and a consistency-improving data augmentation module, a Consistency Teacher Module (CTM), is proposed, which automatically generates entailed questions for a source QA pair and fine-tunes the V QA model if the VZA’s answer to the entailed question is consistent with the sourceQA pair.

TL;DR: This paper shows how combining the visual attention map with the NL representation of relevant scene graph entities, carefully selected using a language model, can give reasonable textual explanations without the need of any additional collected data.

TL;DR: These approaches, based on LSTM-RNNs, VQA model uncertainty, and caption-question similarity, are able to outperform strong baselines on both relevance tasks and are shown to be more intelligent, reasonable, and human-like than previous approaches.