Hacker News new | past | comments | ask | show | jobs | submit login
Pixel Objectness (2017) (utexas.edu)
63 points by lainon 8 months ago | hide | past | web | favorite | 7 comments



Note that there's a more recent paper than the one linked on the project page: https://arxiv.org/abs/1808.04702


Did they cherry-pick the examples? It looks suspiciously good.


It isn't clear from the paper but their appearance model shown in the video segmentation demo is likely the same thing. It shows poor performance at times (see the train at 0:32).

http://vision.cs.utexas.edu/projects/fusionseg/


That's what I was wondering. This is way beyond the level of accuracy that I have seen from anything else.


Honestly, I find this practice unacceptable, and unfortunately I see it a lot. The academic world should frown upon this kind of presentation.


Should have (2017) in the title.


Done. Thanks!




Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact

Search: