The ActivityNet Large Scale Activity Recognition Challenge is a half-day workshop to be held on July 26 in conjuction with CVPR 2017, in Honolulu, Hawaii. In this workshop, we want to stimulate the computer vision community to develop new algorithms and techinques that improve the state-of-the-art in human activity understanding. The data of this challenge is based on the publicily available ActivityNet benchmark.

The challenge focuses on recognizing high-level and goal oriented activities from user generated videos, similar to those found in internet portals.

Keynote Speakers

Jitendra Malik

University of California, Berkeley

Andrew Zisserman

University of Oxford; Google DeepMind


Fabian Caba Heilbron

King Abdullah Universisty
of Science and Technology

Cees Snoek

van Amsterdam

Juan Carlos Niebles

Stanford University

Bernard Ghanem

King Abdullah Universisty
of Science and Technology

Important Dates

April (TBD), 2017: Development kit and data will be available.
June (TBD), 2017: Challenge submission deadline
June (TBD), 2017: Paper submission deadline
July (TBD), 2017: Winners announcement
July 26, 2017: Workshop day