Everybody Dance Now · HackerPapers discussions

Everybody Dance Now — mentioned by belter

Fri, 22 Dec 2023 16:40:11 GMT

You do realize your comment, is endorsing changing the title of a research paper published by respected researchers of the Department of Physics by Illinois State University, Yale University and the Max Planck Institute for Astrophysics? What is next? For example have you heard about this paper? "Attention is all you need" ? - https://arxiv.org/pdf/1706.03762.pdf Atrocious title! And what about "Everybody Dance Now" - https://arxiv.org/pdf/1808.07371.pdf Even worst...

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

Everybody Dance Now — mentioned by all2

Sat, 10 Nov 2018 16:44:15 GMT

I saw a 2 Minute Papers video that talks about the paper [0] I linked below. Basically the AI segments up the human body in to pieces. Using that data you could create a classifier for either pre-defined postures/positions or let it create its own classes (naive classification, I think?) Source [1] is a different kind of segmentation. I think your biggest obstacle will be training sets (assuming you want to use AI/ML). Once you've got training sets, the presence of obstacles (sheets/blankets) might not be so much of an issue. [0] https://arxiv.org/abs/1808.07371 [0]…

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

Everybody Dance Now — HN submission

Mon, 27 Aug 2018 11:29:13 GMT

Everybody dance now

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Everybody Dance Now — HN submission

Sat, 25 Aug 2018 15:35:37 GMT

Everybody Dance Now

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Everybody Dance Now — mentioned by duck

Fri, 24 Aug 2018 01:44:16 GMT

Related paper: https://arxiv.org/abs/1808.07371

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

Everybody Dance Now — mentioned by dsr12

Thu, 23 Aug 2018 20:18:20 GMT

Paper: https://arxiv.org/pdf/1808.07371.pdf

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