Search Results for author: Ashwin K. Vijayakumar

Found 3 papers, 1 papers with code

Sound-Word2Vec: Learning Word Representations Grounded in Sounds

no code implementations EMNLP 2017 Ashwin K. Vijayakumar, Ramakrishna Vedantam, Devi Parikh

In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding.

Word Embeddings

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

20 code implementations7 Oct 2016 Ashwin K. Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra

We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

Image Captioning Machine Translation +3

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