MPI-INF Logo
D6
Visual Computing and Artificial Intelligence

Research Interests

  • Human motion synthesis
  • Machine learning in Vision and Graphics
  • Motion Synthesis in Virtual/Augmented Reality

Publications

Anindita Ghosh, Noshaba Cheema, Cennet Oguz, Christian Theobalt and Philipp Slusallek. "Synthesis of Compositional Animations from Textual Descriptions". Proceedings of ICCV 2021. [Poster]

Anindita Ghosh, Noshaba Cheema, Cennet Oguz, Christian Theobalt and Philipp Slusallek. "Text-Based Motion Synthesis with a Hierarchical Two-Stream RNN". SIGGRAPH 2021. [Poster]

Sahil Bansal, Anindita Ghosh , Chandra Sekhar Seelamantula, Gurunath Gurrala and Prasanta Kumar Ghosh. "Adaptive frequency estimation using iterative DESA with RDFT-based filter". IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) 2017. [Oral]

Dibyabiva Seth, Anindita Ghosh , Ariruna Dasgupta and Asoke Nath. "Real Time Sign Language Processing System". International Conference on Smart Trends for Information Technology and Computer Communications, 2016. [Oral]

Teaching

Recent Positions

Education

Research Projects

    Synthesis of Compositional Animations from Textual Descriptions [Webpage] [Code]

  • Aim: To generate an appropriate sequence of 3D human poses corresponding to complex natural language text input describing single or simultaneous actions.
  • Designed a two-stream hierarchical sequence-to-sequence network that learns a joint embedding of language and poses of the upper and the lower bodies.

Awards

  • Best Master’s Project Award 2016. From St. Xavier’s College, Kolkata, India, for the project “Real-Time Sign Language Processing System”.
  • Certificate of Merit 2013. From St. Xavier’s College, Kolkata, India, for securing the highest score in second year of Bachelor of Science in Computer Science.
  • Vidyasagar Scholarship 2009. From the Government of West Bengal, India, for securing second rank among girls in Kolkata in the statewide 10th standard examination.