ACM MM Grand Challenge on

Large-scale Human-centric Video Analysis in Complex Events


Introduction

The development of modern intelligent city highly relies on the advancement of human-centric analysis technologies. Intelligent multimedia understanding is one of the essential technologies for visual analysis which requires many human-centered and event-driven visual understanding tasks such as human pose estimation, pedestrian tracking and action recognition.

In this grand challenge, we focus on very challenging and realistic tasks of human-centric analysis in various crowd & complex events, including subway getting on/off, collision, fighting, and earthquake escape (cf. Figure. 1). To the best of our knowledge, few existing human analysis approaches report their performance under such complex events. With this consideration, we further propose a dataset (named as Human-in-Events or HiEve) with large-scale and densely-annotated labels covering a wide range of tasks in human-centric analysis.

Our HiEve dataset includes the currently largest number of poses (>1M), the largest number of complex-event action labels (>56k), and one of the largest number of trajectories with long terms (with average trajectory length >480). More information and details about our dataset can be found here.

Four challenging tasks are established on our dataset, which aims to bring together researchers in the multimedia and computer vision communities to enhance the performance of human motion, pose, and action analyzing methods in 3 aspects:

Organize challenges on our large-scale dataset with a comprehensive tasks of human-centric analysis and facilitate the multimedia & AI researches & applications in human-centric understanding.

Encourage and accelerate the develop of new techniques in the areas of human-centric analysis and understanding in complex events.

Foster new ideas and directions on “Large-scale human-centric visual analysis in complex events”.

At the end of the Challenge, all teams will be ranked based on objective evaluation. The top-3 performing teams in each track will receive certificates and awards. At the same time, teams of high performance results are invited to submit challenge papers (4-pages) and present their solutions during the conference.

Figure 1: Samples of various complex events such as (a) dining in canteen, (b) earthquake, (c) getting-off train, and (d) bike collision.
           
(a) (b) (c) (d)

Organizers

Weiyao Lin

Shanghai Jiao Tong University, China

Guojun Qi

Futurewei Technologies, MAPLE Lab, USA

Nicu Sebe

University of Trento, Italy

Ning Xu

Adobe Research,
USA

Hongkai Xiong

Shanghai Jiao Tong University, China

Mubarak Shah

University of Central Florida, USA

News

• June 30: NEW! The challenge result has been released, please refer to the Top-5 teams or the complete LeaderBoard for detailed information.

• June 22: Result submission has been closed! The challenge result notification will be released in June 30, 2020.

• May 18: Result submission start!

• May 17: Registration for our challenge has been closed. However, we will re-open registration after the challenge (in around September). You are welcomed to use our HiEve dataset & website to evaluate your reseach works then.

• May 11: Testing dataset has been released.

• May 10: The paper for our dataset is released. Please click here to download.

• May 9: The deadlines of registration, result & paper submission have been exteneded. See Important Dates for details.

• May 4: Training dataset has been released.

• April 15: Registration for our challenge is now open.

• March 10: Website online.

Tracks

  • Track-1: Multi-person Motion Tracking in Complex Events
  • Track-2: Crowd Pose Estimation in Complex Events
  • Track-3: Crowd Pose Tracking in Complex Events
  • Track-4: Person-level Action Recognition in Complex Events

  Please refer to the Tracks page for detailed information about datasets and tracks.

How To

Register an account for evaluation and refer to the Tracks page to learn about the datasets and tracks of the challenge.

• Download datasets at Data page to train your models, code for evaluating your model performance in training set could be obtained here.

• Submit results of the test set to our evluation server.

• After a while, check your evaluation results on LeaderBoard page.

More information and rules can be found here.

Important Dates

Registration Open April 15, 2020
Training dataset released May 4, 2020
Testing dataset released May 11, 2020
Registration Close May 17, 2020 (was May 13, 2020)
Result submission start May 18, 2020
Result submission close June 22, 2020 (was June 15, 2020)
Challenge result notification June 30, 2020 (was June 22, 2020)
Paper submission deadline July 13, 2020 (was June 29, 2020)