Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling

no code implementations • 21 Sep 2018 • Choongyeun Cho, Benjamin Antin, Sanchit Arora, Shwan Ashrafi, Peilin Duan, Dang The Huynh, Lee James, Hang Tuan Nguyen, Mojtaba Solgi, Cuong Van Than

This paper presents the Axon AI's solution to the 2nd YouTube-8M Video Understanding Challenge, achieving the final global average precision (GAP) of 88. 733% on the private test set (ranked 3rd among 394 teams, not considering the model size constraint), and 87. 287% using a model that meets size requirement.

General Classification Video Classification +1

Towards ontology driven learning of visual concept detectors

no code implementations • 31 May 2016 • Sanchit Arora, Chuck Cho, Paul Fitzpatrick, Francois Scharffe

The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media.

Active Learning Object Recognition