Subhashini Venugopalan
Computer Science Ph.D. student

I work in the intersection of natural language processing, computer vision and machine learning. My advisor is Prof. Ray Mooney and I'm a member of the Machine Learning Group at UT Austin.

I am fortunate to also work with Prof. Trevor Darrell's group at UC Berkeley and with Prof. Kate Saenko at UMass Lowell. The last couple of summers I worked on computer vision and deep learning projects at Google Research (host: Varun Gulshan) and Google Brain (host: Andrea Frome). Prior to joining UT, I spent a year at IBM Research, India (Blue scholar).

In 2011, I obtained a Masters degree in Computer Science and Engineering from IIT, Madras. My thesis was advised by Prof. C. Pandu Rangan. In 2009, I graduated with a bachelor's degree in Information Technology from NITK, Surathkal.


Research

I apply machine learning algorithms along with natural language processing and computer vision techniques to generate descriptions of events depicted in videos.


Publications


Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text
Subhashini Venugopalan, Lisa Hendricks, Raymond Mooney, Kate Saenko

Conference on Empirical Methods in Natural Language Processing, Austin, Texas, November 2016. (EMNLP 2016)
  • [+Abstract]
  • [PDF]
  • [Code]
  • [Project Page]

Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
Lisa Hendricks, Subhashini Venugopalan, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Trevor Darrell

IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, June 2016. (CVPR 2016)
  • [+Abstract]
  • [arXiv]

Sequence to Sequence - Video to Text
Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Raymond Mooney, Trevor Darrell, Kate Saenko

International Conference on Computer Vision, Santiago, Chile, December 2015. (ICCV 2015)
  • [+Abstract]
  • [PDF]
  • [Code]
  • [Project Page]

Translating Videos to Natural Language Using Deep Recurrent Neural Networks
Subhashini Venugopalan, Huijun Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko

North American Chapter of the Association for Computational Linguistics, Denver, Colorado, June 2015. (NAACL-HLT 2015)
  • [+Abstract]
  • [PDF]
  • [Code]
  • [Project Page]

Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Jeff Donahue, Lisa Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell

IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, June 2015. (CVPR 2015)
  • [+Abstract]
  • [PDF]
  • [Project page]

Integrating Language and Vision to Generate Natural Language Descriptions of Videos in the Wild
Jesse Thomason*, Subhashini Venugopalan*, Sergio Guadarrama, Kate Saenko, Raymond Mooney
*equal contribution

International Conference on Computational Linguistics, Dublin, Ireland, August 2014.(COLING 2014)
  • [+Abstract]
  • [PDF]
  • [Code]
  • [Project Page]

YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-shot Recognition
Sergio Guadarrama,Niveda Krishnamoorthy, Girish Malkarnenkar, Subhashini Venugopalan, Raymond Mooney, Trevor Darrell, Kate Saenko

International Conference on Computer Vision, Sydney, Australia, December 2013.(ICCV 2013)
  • [+Abstract]
  • [PDF]
  • [Poster]


Other Research

In the past I have researched on topics in public policy, theoretical cryptography and social network analysis.


Topic based classification and pattern identification in patents
Subhashini Venugopalan, Varun Rai

Technological Forecasting and Social Change, 2014
  • [+Abstract]
  • [PDF]

People and Entity Retrieval in Implicit Social Networks
Suman K. Pathapati, Subhashini Venugopalan, Ashok P. Kumar, Anuradha Bhamidipaty

IEEE International Conference on Internet Multimedia Systems Architecture and Application, Bangalore, India December 2011. (IMSAA 2011)
  • [+Abstract]
  • [PDF]

A New Approach to Threshold Attribute Based Signatures
S. Sharmila Deva Selvi, Subhashini Venugopalan, C Pandu Rangan

  • [+Abstract]
  • [PDF]

Contact


github.com/vsubhashini