Topic provider

Expo Union, which was established in 2003, is actively collaborating with government agencies, associations, and private sectors to organize professional exhibitions related to ecotechnologies, such as “Circular Economy Taiwan” and “Taiwan Water.” Besides, Expo Union hosted some International Medical Conferences and governmental conferences, such as FinTech Taipei 2018(Institute for Information Industry,III), Green Energy and Frontier products Expo 2018 (Academia Sinica),World Congress on Information Technology 2017 (Institute for Information Industry,III), Asia Pacific Academy of Ophthalmology Congress 2016(The Ophthalmological Society of Taiwan). Moreover, it has organized the Marathon Expo for the masses in recent years.

A successful Expo not only requires manpower from all fields with a variety of professional abilities, but also time and effort. Site planning, Exhibition affairs, tender process are equally important. Moreover, it is essential to provide customized and a high-quality design based on customers’ needs. Expo Union has profound experience in organizing international exhibitions and has the most professional team which pays attention to every detail. Last but not least, the company aims to creates maximum values by making all-out effort, professional work division, quality communication, and careful control on cost and time to organize an excellent campaign.

Computational Intelligence Technology Center (CITC) is the first big data R&D center to bridge the big data technology across industries in Taiwan. CITC aims to develop intelligent analytics technologies to boost Artificial Intelligence and big data core capabilities for local IT software companies, also to apply intelligent analytics to help the related industries to enhance their productivity and create new business opportunities. The cross-disciplinary approach enables CITC’s core technology capabilities to provide intelligent analytics and machine learning algorithms that industries need. CITC develops an open Artificial Intelligence and big data platform to create solutions that facilitate the innovative application for service design and business model for industries.

2020/03/25 議題重新開放報名

1. 本議題重新開放報名,點選右方報名鈕即可。 2. 因運算資源有限,報名人數設有上限,額滿後關閉報名功能。 3. 提供Dockerfile,連結:https://reurl.cc/mdaj8j 。 4. 可至上述連結下載範例檔,檔名為pytorch-retinanet.zip 。 5. 上傳檔案需小於100MB。 6. 上傳即可獲得上傳禮,數量有限,送完為止。


This topic refers to the 2018 Marathon Expo, which was held in Taipei World Trade Center Exhibition Hall and lasted for three days, data contains 38,000 images taken from the camera set at the entrance.
The location and gender (male, female, and others[note]) of the visitors in the image can be distinguished rapidly by adopting the object detection technique in machine learning, so gender distribution can be known after a preliminary analysis.

For practical application, visitors’ behaviors and preferences can be analyzed by incorporating data from other devices (i.e. mobile phone). This information can be the reference of route arrangements and booth setup, exhibitors can also plan stands location and activities based on the preference of visitors.

This topic adopts a new competition mode: Participants will upload the analysis program to Aldea, the program will be executed by the platform; original data will only be kept on the platform, and the contest is going to be proceeded with no raw data released.

The purpose of this competition mode is to protect sensitive data, no data will be released on the platform, instead, the data will be read by the uploaded analysis platform. Participants can download container images and develop programs inside the container to ensure the program compatibility.

Notes: “Others” in gender category refers to cases that gender cannot be judged by their appearances, such as children and infants.


Competition Mode

【Remote execution environment】

  1. Execution: Aldea will execute the program after analysis program is uploaded to Aldea by the participants. The contest is going to be proceeded with no raw data released.
  2. Remote execution environment is a computing environment, which contains two parts: environment for program executing (Python is supported), and data that needs to be analyzed (training sets as well as test sets). After participants upload their analysis program to Aldea, the program will be executed in the computing environment and the result (csv) will be sent to the module to calculate the scores, which will be shown on Aldea. Compared to traditional challenges (participants download the data, perform the analysis, build the model and then upload), this competition mode can protect sensitive data since all the data will only be kept on the platform.
  3. This computing environment uses the techniques of containers. Participants can download container image and develop programs inside the container.
  4. The file of container image is the same as the file in the remote execute environment so that program compatibility is ensured.
  5. Participants develop analysis programs based on sample images, which contains images and labels.
  6. Participants can improve and adjust their algorithms of analysis program referring to their score on the platform.
  7. After uploading the program, the maximum time of program execution is 4 hours per submission.



  1. There is a limit on the number of enrollments given that the competition mode and function of this topic are still in a test phase. For those who wants to enroll in this contest, please send us an email. A reply will be given after the evaluation of your related information, if you are determined eligible, then you are welcomed to join the contest.
  2. Please complete account registration on AIdea and then send an email to AIdea(admin.AIdea@itri.org.tw) with a subject of [“Characteristics analysis of exhibition visitors” enrollment], and the information below should be included: platform account, email.
  3. Related experiments of image analysis (such as other topics on Aldea or other similar contests)



  1. For the enrollment, please refer to the description mentioned above.
  2. Prepare a Docker environment, and download container image (docker pull nvaitc/ai-lab:19.08), which is the program development environment.
  3. Download sample images, and develop analysis program based on the images.
  4. Name the analysis program “main.py,” and pack it into a ZIP file (i.e. prog.zip). If there are other files, pack them in the ZIP file together.
  5. The analysis program “main.py” should produce “result.csv” as output (please refer to the “Upload Format Description” for format requirements). If there is no “result.csv” files output, it will be considered as format error.
  6. AIdea’s computing section will perform score computation once “prog.zip” was uploaded to the platform, including training and test datasets.
  7. The score will be shown on Aldea after the computation completes successfully. Participants can adjust their algorithms of the analysis program referring to it.



The following awards will be given to the top three participants whose score on the Private Leaderboard meets the baseline(mAP > 0.50):

First place: 150,000 discount points of hicloud + NTD 50,000 (Tax included)

Second place: 100,000 discount points of hicloud

Third place: 50,000 discount points of hicloud

Honorable mention: 50,000 discount points of hicloud (multiple winners, depends on the final result)

Gift Redemption:

  1. A specially made coaster will be given to the participants who submit their results.
  2. Gift supplies are limited, redemption of coaster is available on a first-come first-served basis.
  3. Each account can redeem 1 coaster only.


※ Participants are welcomed to test the smoothness or other related operating conditions of the platform, and are also encouraged to give feedbacks through forum discussion or admin mailbox (the forum shall have the priority). The one who gives the most valuable and the largest number of feedbacks can receive the honorable mention award!


Hicloud discount points were provided by Chunghwa Telecom


1. Hicloud points can redeem service charge. After the discount, the price will be charged at 30% off based on the list price automatically.

2. Chunghwa Telecom deserves the right to make changes to the terms and conditions herein.

3. The example of discount points calculation can be referred to https://aidea-web.tw/computing


Activity time

The activity time will be based on Taiwan Standard Time (UTC+8), and the schedule is as follows.

2019/12/25Competition begins
2020/01/15Sample image, training set and test set announced
2020/02/19Upload begins
2020/04/29Competition ends


Evaluation Criteria

Evaluations are conducted by adopting mean Average Precision (mAP) [1] using Intersection over Union(IoU)[2] and the threshold is 0.5. The result is True Positive (TP) if the loU of predictive object box and labeling object box is greater than 0.5, otherwise it’s False Positive (FP), and Precision index can be determined. Consequently, the system will evaluate every object to determine its AP (Average Precision) points. The mAP will then be calculated by compute the average AP points of the three gender categories. The ranking of the competitors will be based on this value. We adopt COCO API [3] to calculate the evaluated value of mAP.

[1] Average Precision (AP):

[2] intersection over union (IoU):



  • The evaluation will be based on the final uploaded result. If multiple participants get the same evaluation scores, the time of uploading will determine the ranking.
  • The maximum number of uploading times is 2 times per day.
  • Using external data sets is allowed. However, for equity, if external data sets are used, their instructions and references should be stated in the forum for references.
  • All the data, techniques and source codes are original work of participants or are used by permission complying with laws and regulations. If any third-party claims their intellectual property rights or other rights and interests are being violated, the participant will need to handle the disputes personally. If any participants violate intellectual property rights, they will be disqualified, and shall bear legal responsibilities.
  • All the achievements and their IPRs (intellectual property rights) belong to the participants, and the Copyright License Agreements, patent applications, technology transfer and equity distributions of them, should be in accordance with the relevant Laws and Regulations.
  • This topic does not offer a team-up option, only one account per person is allowed, and each person can only participate once. If any violations are found, people who are involved would be forced to withdraw the activity.
    If there is cheating or fraud during the activity, such as exchanges and discussions between different accounts the team that cheats will be disqualified from the activity and the vacancy would be filled up by other teams in the ranking order.
  • After uploading, the maximum program execution time of the computing section is 4 hours.
    After uploading, the answers of test data would be divided into two parts to calculate the score:
    • Before the deadline of the activity: The system refers to only a part of the test data to examine and calculate the score. The result will be posted on Public Leaderboard
      as reference for the final score and ranking. This data accounts for 50% of the entire test data.
    • After the deadline of the activity: The system refers to the remaining test data (50%) to examine and calculate the score. The result will be posted on Private Leaderboard as reference for the final score and ranking.
      For those who have signed up for this competition, you acknowledge that you have read, understood, and agreed to be bound by the terms and regulations of this activity.
  • For participants who violate relevant terms or regulations, will be disqualified from the activity, if any of the violators has been awarded, the prize will be revoked, and the participants will need to return the prize money as well as certificate.
  • Should there be disputes, the organizer reserves the right to make the final decision.