2 Hits in 0.92 sec

ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems [article]

Yinda Zhang, Sameh Khamis, Christoph Rhemann, Julien Valentin, Adarsh Kowdle, Vladimir Tankovich, Michael Schoenberg, Shahram Izadi, Thomas Funkhouser, Sean Fanello
2018 arXiv   pre-print
Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of 1/30th of a pixel; it does not suffer from the common over-smoothing issues  ...  The proposed loss is optimized using a window-based cost aggregation with an adaptive support weight scheme.  ...  .: Low compute and fully parallel computer vision with hashmatch. (2017) 47. Wang, S., Fanello, S.R., Rhemann, C., Izadi, S., Kohli, P.: The global patch collider. CVPR (2016) 48.  ... 
arXiv:1807.06009v1 fatcat:g4su4zk37jdpblr4xubxuihbii

Algorithmic content moderation: Technical and political challenges in the automation of platform governance

Robert Gorwa, Reuben Binns, Christian Katzenbach
2020 Big Data & Society  
Despite the potential promise of algorithms or 'AI', we show that even 'well optimized' moderation systems could exacerbate, rather than relieve, many existing problems with content policy as enacted by  ...  toxic speech; and identifies key political and ethical issues for these systems as the reliance on them grows.  ...  For instance, feature detection algorithms in computer vision ensure that even if an image is rotated or scaled, the same shapes can be identified when they are upside down or enlarged (Harris and Stephens  ... 
doi:10.1177/2053951719897945 fatcat:x225nettzrbvbkcqretvqstnji