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 three different publicily available datasets: ActivityNet, ActivityNet Captions, and Kinetics. The challenge focuses on recognizing high-level and goal oriented activities from user generated videos, similar to those found in internet portals.