Trevor Darrell receives ICML Test-of-Time Award

EECS Professor Trevor Darrell and his team have been awarded the prestigious Test-of-Time Award at the International Conference on Machine Learning (ICML) for their 2014 paper, “DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition.” The award celebrates the lasting impact of a paper over the past 10 years in the field of machine learning. The paper, co-authored by Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell, has had a significant impact, particularly in the area of visual recognition.

The award ceremony took place in Vienna, Austria, celebrating the contributions of this influential work. This recognition marks the third Test-of-Time award for papers associated with the Caffe framework this summer.

In June, the paper “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” authored by Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik, received the CVPR Longuet-Higgins Test-of-Time Prize. In May, the paper “Caffe: Convolutional Architecture for Fast Feature Embedding,” co-authored by Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell was honored with the ACM SIGMM Test-of-Time Award.