Ashwin Kalyan

I am a Ph.D student at Georgia Tech advised by Prof.Dhruv Batra. I primarily study deep learning and vision.

I am also a violinist learning Karnatic Classical music from Vid. A Kanyakumari . Sounds from concerts are on my soundcloud channel.

Publications :

• Sound-word2vec: Learning Word Embeddings Grounded in Sound [arxiv]
  Ashwin K Vijayakumar, Ramakrishna Vedantam, Devi Parikh
  arxiv pre-print
  
• Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models [arxiv] [code] [demo]
  Ashwin K Vijayakumar, Michael Cogswell, Ramprasaath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra
  Draft of ongoing work
• Estimating Multiple Physical Parameters from Speech Data
  Shareef Babu Kalluri, Ashwin K Vijayakumar, Deep Vijayasenan, Rita Singh
  IEEE Workshop on Machine Learning for Signal Processing (MLSP), 2016
  
• We Are Humor Beings: Understanding and Predicting Visual Humor [arxiv]
  Arjun Chandrasekaran, Ashwin K Vijayakumar, Stanislaw Antol, Mohit Bansal, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
  
• Audio Segmentation using A-priori Information in the Context of Karnatic Music [Xplore]
  Ashwin K Vijayakumar, Sreecharan S, Sumam David S
  IEEE Conference on Signal Processing, Informatics, Communication and Energy Systems, 2015