Competition

ACM MM'24 Multimodal Gait Recognition Challenge (Track 4)

Organized by Haofeng_Chen - Current server time: March 30, 2025, 6:27 a.m. UTC

First phase

Development
July 25, 2024, midnight UTC

End

Competition Ends
Oct. 1, 2024, midnight UTC

Timeline:

  • Register date: July 15th, 2024.
  • Release of training data: July 25th, 2024.
  • Open for submission on validation set: August 1st, 2024.
  • Submission deadline on validation set: September 20th, 2024.
  • Open for submission on test set: September 21th, 2024.
  • Submission deadline on test set: October 1st, 2024.
  • Submission deadline for the technical report: October 15th, 2024.
  • Winner and invitation speakers: No later than October 20th, 2024.

Welcome to the MGR Challenge!

ACM MM'24 MGR Challenge Offical WEBSITE IS HERE!

We invite you to participate in the ACM Multimedia 2024 shared task on Multimodal Gait Recognition —— MGR Challenge. We seek to harness these advancements by encouraging participants to develop novel algorithms and systems that effectively combine and utilize various gait data. The goal is to create solutions that can perform robust gait recognition in real-world environments, overcoming the limitations of traditional systems and paving the way for new applications and innovations.

The task of the fourth track is the Multi-modal Gait Recognition Track.

Our competition has four tracks, see other:   Track 1,  Track 2 ,  Track 3

Datasets

Our dataset has several featured properties:

  • In-the-wild: We collected the dataset from a completely unconstrained environment, where people often walk at irregular routes and speeds, with complex backgrounds, and may be obscured by other people or objects.
  • Multi-modal: It contains parsing, silhouette, 2D pose, and SMPL parameter, which can be used to develop multi-modal gait recognition algorithms.
  • High-quality: To ensure the quality of the dataset, we employed a professional annotation team to further clean data at the end of each critical step.

Dataset Acquisition: After clicking the "Participate", you can obtain the required datasets of this track in the "Get Data" column.

Evaluation Phases:

  • Phase 1: development phase.  We provide you with labeled training data and unlabeled validation data. The performance of your LAST submission will be displayed on the leaderboard.
  • Phase 2: final phase.  We provide you with unlabeled test data. The performance of your LAST submission will be displayed on the leaderboard.

Evaluation protocol:

  • Evaluation metrics:
    • Rank-1: The probability that the correct match appears as the first result in the retrieval list.
  • Submissions to the Leaderboard must be made in the form of a zip file containing the predicted CSV file with the following filename:

submission.csv

Challenge Rules

Participants of this challenge acknowledge that they have read and agree to the following rules:

  • Only fully automated methods will be accepted as submissions; manual annotations and interactive methods are not permitted.
  • Each participant must create a CodaLab account to register. Only one account per user is allowed.
  • Participants are allowed to form teams without limitations on the number of team members. However, a participant may not participate in more than one team.

Development

Start: July 25, 2024, midnight

Description: Development phase: create models and submit results on validation data. The performance of your LAST submission will be displayed on the leaderboard.

Final

Start: Sept. 21, 2024, midnight

Description: Final phase: we provide you test data. The performance of your LAST submission for results on test data will be displayed on the leaderboard.

Competition Ends

Oct. 1, 2024, midnight

You must be logged in to participate in competitions.

Sign In