• MultiSeg: Parallel Data and Subword Information for Learning Bilingual Embeddings in Low Resource Scenarios.
    Proceedings of the 1st Joint Workshop of SLTU (Spoken Language Technologies for Underresourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) (SLTU-CCURL 2020)
    Efsun Kayi *, Vishal Anand *, Smaranda Muresan.
    12 months of work and 6.7 Terabytes of data, Columbia University, Computer Science
    [paper] [code] [visualization]

  • Story Semantic Relationships from Multimodal Cognitions.
    Proceedings of the 28th ACM Multimedia Conference, Seattle, USA, October 2020.
    Vishal Anand, Raksha Ramesh, Ziyin Wang, Yijing Feng, Jiana Feng, Wenfeng Lyu, Tianle Zhu, Serena Yuan, and Ching-Yung Lin.

  • Kinetics and Scene features for intent detection. Oral Presentation.
    Proceedings of the International Workshop on Deep Video Understanding (DVU2020) (ACM ICMI 2020, Netherlands, October 2020
    Raksha Ramesh, Vishal Anand, Ziyin Wang, Tianle Zhu, Wenfeng Lyu, Serena Yuan, and Ching-Yung Lin.

  • Security (AR - NLP) approaches for virtual reality transactions,
    Vishal Anand.
    Patent Filed, 152 PCT countries, Aug 2017. Published Feb 2019
    US Patent App. 15/184,759, Visa Inc.

  • Systems and methods (Analytics) for preventing fraud,
    Vishal Anand.
    Patent Filed, 152 PCT countries, Jun 2016. Published Dec 2017
    US Patent App. 15/674,187, Visa Inc.

  • NLP based pre-event occurence prediction,
    Vishal Anand.
    Trade Secret, Visa Inc.

  • On Optimizing Human-Machine Task Assignments,
    Multiple authors (top-researcher).
    In the proceedings of Human Computation and Crowdsourcing, San Diego, USA, Nov 2015.
    was introduced to serious academia research via this work

  • Deep Learning NLP Architecture of word vectors (causality evaluation in multi-task frameworks),
    Vishal Anand.
    Bachelors Thesis, IIT Guwahati, Computer Science, April 2015