Profile cover photo
Profile photo
Meng Lin
About
Meng's interests
View all
Meng's posts

Post has attachment
Dreams come true, how about that http://www.dell.com/us/business/p/xps-13-linux/pd

Post has attachment
Proper productivity booster #DeskBeers http://bit.ly/17AvlkR

Post has attachment
This is impressive, but really hurts my eyes. #scrollslow http://bit.ly/1xYFd0j

Post has attachment
#Sony, ha: Did North Korea Really Attack Sony? #hack http://bit.ly/1AZ3o11

Post has attachment

Post has attachment

Post has attachment
Think about Easter Islanders, we might just have been lucky so far: The #Fermi Paradox http://bit.ly/146HXPf

Post has shared content
A Glimpse into Computer Vision

Neural networks have recently had great success in significantly advancing the state of the art on challenging image classification and object detection datasets. However, this accuracy comes at a high computational cost both at training and testing time.

But what if one takes inspiration from how people recognize objects, by selectively focusing on the important parts of an image instead of processing an entire image at once? By ignoring irrelevant noisy features in an image, fewer pixels need to be processed, substantially reducing classification and detection complexity.

Last week, during #NIPS2014 (goo.gl/uEHYAt), Google DeepMind presented Recurrent Models of Visual Attention, a paper which describes an “attention-based task-driven visual processing” that is capable of extracting information from an image or video by adaptively selecting a sequence of smaller regions (glimpses), processing only selected regions at high resolution. 

Read the full paper at http://goo.gl/dEdWkk
Photo

Post has attachment
Welcome to the New Compiler Arms Race: #V8
http://mlin6436.github.io/blog/v8/

Post has attachment
Tube design for #2020, 2020!? http://bit.ly/1xOR1S0
Wait while more posts are being loaded