My research specializes in developing neural network architectures for 3D motion analysis, modeling, and synthesis. My work involves leveraging advanced deep learning models, including transformers, diffusion models, and large visual-language models, for applications in motion-conditioned synthesis and multi-modal generation. I am passionate about applying these techniques to solve complex problems in computer vision and AI.

	ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, Philipp Slusallek European Conference on Computer Vision (ECCV), 2024 [Project page]
	IMoS: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, Philipp Slusallek EUROGRAPHICS Computer Graphics Forum 42 (2), 1-12, 2023
	Synthesis of Compositional Animations from Textual Descriptions Anindita Ghosh, Noshaba Cheema, Cennet Oguz, Christian Theobalt, Philipp Slusallek International Conference on Computer Vision (ICCV) 2021. [Paper] [Poster] Also accepted as a poster: "Text-Based Motion Synthesis with a Hierarchical Two-Stream RNN". ACM SIGGRAPH 2021. [Poster]

• June, 2024 - September 2024:
  Research Intern at Snap Research , New York City, NY, USA
  Worked on music driven two-person 3D dance motion synthesis.
  Supervisor: Dr. Bing Zhou
• June, 2023 - September 2023:
  Research Intern at Google Research , Mountain View, CA, USA
  Working with the Talking heads group on facial expression (particularly lip motion) synthesis from audio input for visual dubbing.
  Supervisor: Dr. Avisek Lahiri, Dr. Vivek Kwatra
• August, 2021 - Present:
  Researcher at the German Research Centre for Artificial Intelligence (DFKI) , Saarbücken
  Working with the Agents and Simulated Reality group on Human motion analysis, modelling and synthesis.
  Supervisor: Dr. Philipp Slusallek
• April, 2020 - September, 2020:
  Tutor for Image Processing and Computer Vision at Saarland Informatics Campus, Saarbücken.
  Delivered tutorials, graded assignments and exams. Contact person: Prof. Joachim Weickert
• May, 2019 - July, 2021:
  Researche Assistant at the German Research Centre for Artificial Intelligence (DFKI) , Saarbücken
  Worked with the Agents and Simulated Reality group on parts of natural human motion simulation software and deep learning based text to motion synthesis.
  Advisors: Erik Herrmann, Noshaba Cheema

• November 2021 - present:
  Ph. D. in Computer Science at the Universität des Saarlandes, Saarbrücken, Germany and the Max-Planck-Institut für Informatik. (supervisors: Prof. Dr. Philipp Slusallek, Prof. Dr. Christian Theobalt)
  
• October 2018 - July 2021:
  Master of Science in Visual Computing at the Universität des Saarlandes, Saarbrücken.
  Master's Thesis: Synthesizing Compositional Animations from Textual Descriptions Using an RNN-based Hierarchical Two-Stream Network (supervisor: Prof. Dr. Philipp Slusallek)
• 2014 - 2016:
  Master of Science in Computer Science at the St. Xavier's College, Kolkata, India.
  Master's Thesis: Real Time Sign Language Processing System. (supervisor: Prof. Dr. Asoke Nath)
• 2011 - 2014:
  Bachelor of Science in Computer Science at the St. Xavier's College, Kolkata , India.

• Speaker at SIGGRAPH 2023 Frontiers Workshop: Expressive Avatar Interactions in Online Co-Experiences.