- 🎥 Multimodal Video Captioning - Audio-Visual understanding
- 👁️ Computer Vision - 3D Reconstruction, Pose Estimation
- 🤖 Vision Transformers - Attention mechanisms for visual tasks
- 📊 Deep Learning Research - PyTorch implementations
- 🌐 Portfolio | 📧 ashokbk215@gmail.com
"Researching multimodal AI systems for real-world applications"