Challenge Registration

Register your team to participate in this challenge by filling out the registration form on the following link

Participation 

The challenge is open to both students and working individuals.

A. Registration Requirements

• Mandatory Registration
  All participants, including solo challengers, must complete and submit the Team Registration Form prior to joining the competition. 

• In the form, fill in the following fields:

  • Title: Enter your team name.

  • Abstract: This field may be left blank.

  • Track Selection: Choose the specific challenge track your team is participating in.

• Team Size
  There is no restriction on the number of team members, but every team member is expected to contribute actively.

B. Team Composition

• Team Members

  • There is no limit to team size.

  • Only supervisors can participate in multiple teams within the same challenge.

• Special Considerations

  • If creating multiple teams from the same lab, ensure compliance with the No Private Sharing rule.

  • For team mergers, participants must contact the organizers via email.

• Participation Across Challenges

  • Students are allowed to join multiple ABC challenges.

However, students affiliated with the host or organizing laboratories are not eligible to participate.

C. Code and Data Sharing

Private sharing of code or data outside your team is strictly prohibited. Teams must maintain confidentiality to ensure fair competition.

D. Challenge Completion Requirements

To successfully complete the challenge, participants must:

1. Deliverables

Participants must develop a system that processes the provided continuous, non-segmented UWB radar data stream and identifies fall events occurring among normal Activities of Daily Living (ADLs).

1. • The final submission should provide, for each detected fall:

     1. the start time of the fall;

     2. the end time of the fall;

     3. the corresponding fall prediction according to the official submission format.

Participants should submit predictions for all evaluation streams and follow the submission instructions provided by the organizers. The exact file format and submission procedure will be released with the challenge materials.

2. Paper Submission

   • Provide a paper detailing your methodology in alignment with the challenge objectives.

At least one team member is required to present the per in the workshop.

By default, accepted papers will be published under IJABC (International Journal of Activity Behavior and Computing) under Jstage. For paper format, please check the ABC Main website.

Evaluation Guidelines

The evaluation involves both correct fall detection and temporal localization.

Submitted systems will be evaluated according to their ability to:

1. Correctly detect fall events;

2. Avoid missed falls;

3. Minimize false alarms during normal daily activities;

4. Accurately estimate the start time of each fall;

5. Accurately estimate the end time of each fall;

6. Correctly capture the duration of the fall event;

7. Detect falls with minimal delay.

The evaluation is designed to reflect a realistic continuous-monitoring scenario rather than simple file-level classification.

Evaluation Overview

The challenge goal is to evaluate whether a system can detect and temporally localize falls within a continuous UWB radar stream containing realistic Activities of Daily Living.

Predicted fall intervals will be compared with the ground-truth fall intervals using measures including:

Correct Detection — Hit / Miss / False Alarm

Determines whether each real fall was successfully detected and whether incorrect alarms were generated.

Start-Time Error

Measures the difference between the predicted and actual beginning of a fall event.

End-Time Error

Measures the difference between the predicted and actual end of a fall event.

Temporal Intersection over Union (tIoU)

Measures the overlap between the predicted fall interval and the ground-truth fall interval.

Detection Latency

Measures how quickly the system detects a fall after the actual fall begins.

Together, these measures evaluate both whether a fall is detected and how accurately its timing is identified.

Paper Submission

The paper should be written in English, following the ABC formatting guidelines. The paper should be 8-12 pages, including references. The expected contents of the paper are:

• Abstract: A concise summary of the team’s proposed method and the results.

• Methodology: A detailed description of the methodology, including the dataset, preprocessing, model development, and evaluation metrics.

• Results and Discussion: A presentation and analysis of the results and a discussion of the strengths and limitations of the proposed method.

• Conclusion: A summary of the team’s main findings, implications, and suggestions for future work.

• References: A list of references, including three main papers of the challenge (published paper about the dataset, LOPDO evaluation and challenge summary paper). The Challenge Summary Paper will be provided upon confirmation with the hosts. Kindly submit the camera-ready ahead.

For information regarding the Registration for the ABC conference, visit the main ABC2025 website.

Prizes

• The winning team will be awarded 100,000 JPY.

• Each of the participating teams will be awarded a participation certificate.