Multimedia content analysis and synthesis is at the core of our research, with a particular focus on visual and text modality. These are some of the current ongoing projects and thesis directions.
Multimodal Skill Assessment
- Communication and Presentation skill assessment using multimodal analysis (Sowmya Rasipuram, completed and Chinchu Thomas PhD thesis, nearing completion)
- Handwritten Essay grading (Annapurna PhD thesis, nearing completion)
- AI for Social Psychology (Kumar Shubham MS thesis, Rahil iMTech Thesis)
- Dancing skill assessment (Pooja Venkatesh MS thesis, completed)
Multimodal Conversational Systems:
- Follow up question generating interviewing Agent (Pooja Rao MS, PhD thesis)
- Multi code follow up generation (Vibhav iMTech thesis)
- Margadarshi (UPSC interviewing agent, internally funded project)
Motion Capture and Indian Sign Language Synthesis:
- ISL graphics based system (Mphasis funded project, Shyam MS thesis)
- MC: Video to Avatar (Shyam and Vijay Vighnesh RA, MINRO)
- MC: GAN based generation (Shyam and Janmesh RA)