Deep multi-scale video prediction beyond mean square error — mentioned by theGnuMe

Sat, 25 Nov 2023 00:11:32 GMT

This is the cake lecture right? I think it gets mentioned at the end of that talk but he might not have said it then. He also has the part about predictive video (which way does the thing fall). From 2015. https://arxiv.org/abs/1511.05440

Paper and discussion history. A mention is not an endorsement.

Deep multi-scale video prediction beyond mean square error — mentioned by aab0

Thu, 29 Sep 2016 21:36:24 GMT

> Neural networks are good at adaptation, but useless at forming concepts about how the data is structured. For example: in video we do motion compensation, because we know video captures motion since objects move in physical reality. A neural network would have to do the same in order to get the same compression levels. Neural networks know that objects move. See for example https://arxiv.org/abs/1511.05440 http://web.mit.edu/vondrick/tinyvideo/

Paper and discussion history. A mention is not an endorsement.

Deep multi-scale video prediction beyond mean square error · HackerPapers discussions

Deep multi-scale video prediction beyond mean square error — mentioned by theGnuMe

Deep multi-scale video prediction beyond mean square error — mentioned by aab0