TrajNet++ Challenge

August 01-December 31, 2019

Challenge / Overview

Trajectory forecasting in dynamic scenes has become an important topic in recent times because of the increasing demands of emerging applications of artificial intelligence like autonomous cars and service robots.

In the past few years, several novel methods have been proposed for trajectory forecasting. However, most methods have been evaluated on limited data. Furthermore, these methods have been either evaluated on different subsets of the available data or on contrasting coordinate systems (2D, 3D) making it difficult to objectively compare the forecasting techniques.

One potential solution is to create a standardized benchmark to serve as an objective measure of performance. Benchmarks hold great promise in addressing such comparison issues. There have been a limited number of attempts at trajectory forecasting benchmarks, such as the ETH and the UCY datasets. Moreover, a good benchmark requires not only a standard dataset but also proper evaluation metrics.

In this challenge, we introduce TrajNet++, a new, large scale trajectory-based benchmark, that uses a unified evaluation system to test the gathered state-of-the-art methods on various trajectory-based activity forecasting datasets for a fair comparison.

Challenge / URL

Challenge / Co-organizers

Sven Kreiss

Postdoctoral Researcher, EPFL

Alexandre Alahi

Assistant Professor, EPFL

Parth Kothari

Doctoral Assistant, Visual Intelligence for Transport EPFL

AMLD EPFL 2020 / Challenges

Flatland Challenge

With Erik Nygren & Sharada Mohanty

Round 1: July 30-October 13, 2019
Round 2: October 13, 2019-January 05, 2020

AutoTrain Challenge

With Thijs Vogels & Martin Jaggi

October 01-December 15, 2019

D’Avatar - Reincarnation of Personal Data Entities in Unstructured Text Datasets

With Kalapriya Kannan & Balaji Ganesan

October 30-December 31, 2019

AMLD / Global partners