The talk focuses on providing the exposure to the user about the video understanding and the vision transformer, which would help them to explore more about the usecases. Also, various applications that they can build with the Jockey

- Rise of video understanding, Why now?
- Key applications across industries and various usecases
- Building multimodal intelligence to generate video embeddings with Marengo
- Crafting video embeddings that capture meaning
- Understanding about Agentic Video Intelligence
- Potential of the Agentic Video Intelligence (Jockey)
- The research going on and looking forward in this field
- Q&A and open discussion

Duration would be ideal for 20 Mins

No pre-requisite