[ad_1]
This June, the 2020 Conference on Computer Vision and Pattern Recognition (CVPR) went fully virtual, with members of the research community gathering online to discuss key topics and research in the field. Amazon scientists presented 10 papers and participated in a number of co-located workshops and tutorials throughout the conference.
During the event, Gerard Medioni, CVPR general chair and Amazon distinguished scientist, hosted a pre-recorded discussion with two luminaries in the field, Pietro Perona, Amazon Fellow, and Larry Davis, senior principal scientist.
Medioni, Perona, and Davis discussed the history and notable milestones of computer vision science, some of the research they presented during CVPR 2020, and where they see this field of research heading in the future.
Papers and resources mentioned in the discussion:
Machine perception of three-dimensional solids
Roberts, Lawrence G.
What the frog’s eye tells the frog’s brain
J. Y. Lettvin, H. R. Maturana, W. S. McCulloch, and W. H. Pitts
Receptive fields of single neurons in the cat’s striate cortex
D. H. Hubel and T.N. Wiesel
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
D. H. Hubel and T.N. Wiesel
Perceptrons: An introduction to computational geometry (book)
Marvin Minsky and Seymour A. Papert
Determining Optical Flow
Berthold K.P. Horn and Brian G. Schunck
The Binford-Horn LINE-FINDER
Berthold Horn
MIT Summer vision project
Fashion Outfit Complementary Item Retrieval
Yen-Liang Lin, Son Tran, Larry Davis
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
Biagio Brattoli, Joseph Tighe, Fedor Zhdanov, Pietro Perona, Krzysztof Chalupka
Auditory Scene Analysis
Albert S. Bregman
window.fbAsyncInit = function() { FB.init({
appId : '1024652704536162',
xfbml : true, version : 'v2.9' }); };
(function(d, s, id){
var js, fjs = d.getElementsByTagName(s)[0];
if (d.getElementById(id)) {return;}
js = d.createElement(s); js.id = id;
js.src = "https://connect.facebook.net/en_US/sdk.js";
fjs.parentNode.insertBefore(js, fjs);
}(document, 'script', 'facebook-jssdk'));
[ad_2]
Source link