In the image, a person is sitting in front of a whiteboard, presumably engaged in a presentation or brainstorming session. On the screen behind the person, a series of slides is displayed, featuring diagrams and graphs that explain the transformation of video within a system. The diagrams and slides cover topics such as video compression, digital signal processing, and the role of video models in capturing and manipulating visual information. A computer sits next to the whiteboard, likely used to create and edit the presentation materials. The overall scene suggests that the person is preparing or delivering a presentation on video technology to an audience, possibly a colleague or a group of students.
Text transcribed from the image:
Sora
Transformer-based video diffusion models
Peebles et al., Sora, 2024.
Visual
encoder
Shou, NUS
101