Скачать или смотреть Exploring Video AI Foundation Models and Use Cases with James Le

We don’t just have unstructured text data; we also have images, audio, and video. Video understanding and computer vision algorithms have been in existence and used for several decades now. James, head of Developer Experience at TwelveLabs (https://twelvelabs.io/), and I discussed the historical overview of computer vision algorithms, the new state-of-the-art models like Pegasus, and how advanced the technology has become in terms of video understanding, processing, recognition, classification, and more. Check out this episode to gain more knowledge about video understanding, multimodal AI, and developer relations from James. Here are the links to the blogs that James referred to in our conversation:

Video understanding research: https://www.twelvelabs.io/blog/the-pa...

Marengo: https://www.twelvelabs.io/blog/introd...

Pegasus: https://www.twelvelabs.io/blog/upgrad...

#ai #artificialintelligence #genai #llms #computervision #devrel #developers #machinelearning #nlp #unstructureddata