
@ducha_aiki you are probably asking for non-existent capabilities in humans. They (we) ultimately decide Best Paper vs just a poster vs reject
Users are debating the meaningfulness of CVPR Best Paper Awards, with some agreeing the honors lacked value in past years like 2016 while others reject the dismissal by pointing to official award records.

@ducha_aiki you are probably asking for non-existent capabilities in humans. They (we) ultimately decide Best Paper vs just a poster vs reject

@ducha_aiki I got the year wrong (from memory) but the vibes right! Was 2016 (as pointed out below)

@ducha_aiki I agree with the sentiment, but I’m pretty sure ResNet just won test of time, and also won CVPR 2015 best paper award??

@ducha_aiki Seems unlikely (there seems to be a single CVPR paper that won both awards). But anyways, if a paper wins test of time, they will have had impact, so it shouldn’t matter if they released source code originally or not.

@JonathonLuiten You are wrong
https://cvpr2015.thecvf.com/awards.php

@ducha_aiki I stand corrected, there are two such papers.

@SattlerTorsten What are those?

@ducha_aiki @JonathonLuiten I think it was 2016

@ducha_aiki Resnet and “Object Class Recognition by Unsupervised Scale-Invariant Learning”

@KadirYilmaz_CV @JonathonLuiten You are right about 2016
https://tc.computer.org/tcpami/awards/cvpr-paper-awards/

@JonathonLuiten @ducha_aiki But resnet had code and pretrained models available ;)