))
TVV Ep 14 - Codec for AI, Codec of AI, Codec with AI
Manage episode 357308361 series 3369885
Content provided by Visionular. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Visionular or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
In this episode, Professor Maggie Zhu and her student Zhihao Duan describe the state of the art in AI codecs and their diverse applications. AI compression can be applied to video three ways: augmenting conventional video codecs, completely replacing a conventional codec and also to compress the AI models used for various video applications. They discuss how the proliferation of lightweight video-capable devices is driving new applications and changing the balance between encoders and decoders, and how their novel architecture can beat the state of the art. Watch / listen to see where the next generation of technology is taking us!
Watch the full video version.
Learn more about Visionular and get more information on AV1.
Chapters
1. TVV Ep 14 - Codec for AI, Codec of AI, Codec with AI (00:00:00)
2. Coding for AI (00:09:00)
3. Machine learning and AI techniques in the coding pipeline (00:14:01)
4. AI bridges the gap between many fields (00:29:21)
5. Pre-trained method (00:38:38)
6. AI generative models (00:47:29)
7. Codecs of AI (01:00:43)
29 episodes
Share
