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

1. Communication and Presentation skill assessment using multimodal analysis (Sowmya Rasipuram, completed and Chinchu Thomas PhD thesis, nearing completion)
2. Handwritten Essay grading (Annapurna PhD thesis, nearing completion)
3. AI for Social Psychology (Kumar Shubham MS thesis, Rahil iMTech Thesis)
4. Dancing skill assessment (Pooja Venkatesh MS thesis, completed)

Multimodal Conversational Systems: 

1. Follow up question generating interviewing Agent (Pooja Rao MS, PhD thesis)
2. Multi code follow up generation (Vibhav iMTech thesis)
3. Margadarshi (UPSC interviewing agent, internally funded project)

Motion Capture and Indian Sign Language Synthesis: 

1. ISL graphics based system (Mphasis funded project, Shyam MS thesis)
2. MC: Video to Avatar (Shyam and Vijay Vighnesh RA, MINRO)
3. MC: GAN based generation (Shyam and Janmesh RA)