Research Intern — Human Pose Understanding and Vision-Language Models

Tasks

• Apply multimodal learning benchmarks
• Build vision language model pipelines
• Design novel multimodal systems
• Develop deep learning training workflows
• Develop pose understanding models
• Implement video understanding methods
• Model human motion and activity
• Use prompt engineering techniques

Perks/Benefits

• Publication opportunity

Skills/Tech-stack

Computer Vision | Human pose estimation | Language Models | Language Processing | Large Language Models | Multimodal Learning | Natural Language | Natural Language Processing | Pose Estimation | Prompt engineering | PyTorch | Python | Temporal modeling | Video Understanding | Vision Language Models | Vision-language