Loading
Cookies help us deliver our services. By using our services, you agree to our use of cookies. Learn more

crowdAI is shutting down - please read our blog post for more information

ImageCLEF 2018 Lifelog - LMRT

Lifelog moment retrieval


Completed
49
Submissions
47
Participants
2291
Views

ImageCLEF FAQ

Posted by Ivan_Eggel over 2 years ago

What is ImageCLEF?


ImageCLEF 2018 is an evaluation campaign that is being organized as part of the CLEF initiative labs. The campaign offers several research tasks that welcome participation from teams around the world. The results of the campaign appear in the working notes proceedings, published by CEUR Workshop Proceedings (CEUR-WS.org). Selected contributions among the participants, will be invited for publication in the following year in the Springer Lecture Notes in Computer Science (LNCS) together with the annual lab overviews.

Do I have to register with CLEF in order to participate in an ImageCLEF challenge?


Normally you would have to register with CLEF, however we will handle this for you by sending the necessary data you gave us on CrowdAI directly to CLEF. No further action on your behalf is required.

What is an ImageCLEF task?


ImageCLEF is grouped into several so-called tasks, each of them tackling a different research topic. An ImageCLEF task may have have several challenges, but has only one global dataset. If you get access to a challenge’s dataset and that challenge is part of a task providing multiple challenges, you will automatically have access to the data of all challenges in that task. This years tasks are: - ImageCLEF Caption => 2 challenges - ImageCLEF Tuberculosis => 3 challenges - ImageCLEF Lifelog => 2 challenges - ImageCLEF VQA-Med => 1 challenge

How can I get access to the the data of a challenge?


Please read the Rules section in the challenge description page. There are mainly 2 things you have to do: - Add additional information to your profile so you comply with the CLEF requirements - Sign and upload an End User Agreement

When you click on the dataset tab of a challenge you will be guided through the process in order to obtain access to the data. Please note, as already stated above: If you get access to a challenge’s dataset and that challenge is part of a task providing multiple challenges, you will automatically have access to the data of all challenges in that task.

1

Posted by Bashar_Al-Shboul  over 2 years ago |  Quote

Why does it take too long to approve an EUA ?

Posted by Luca_Piras  over 2 years ago |  Quote

Why does it take too long to approve an EUA ? Sorry @Bashar_Al-Shboul, the system does not notificate when an EUA is submitted, we should check regularly but in the last two weeks we have not been so “regular”. I’m sorry for the inconvenience

Posted by AIlab-GTI  about 2 years ago |  Quote

This is the first time we participate to lifelog and we have some (maybe a lot) questions:

1) The questions in devsets XML are the final ones? Are you going to give more?

2) Are you going to give more metadata for the test data?

3) for the 001 of LMRT, do you consider airplane public transport? I wonder because you have it separately from transport activity.

4) considering 002, you say when eating lunch independent of the place. So I guess it is enough to see on the image something that is eaten? How do we know it his? What if it does not appear on an image among others that appear? do we consider he eats in that too?

5) In ADLT, when you ask “how many times” you mean in number of photos or times as total e.g. ate 6 times..

6) 007…Working (exclude meetings)…when he talks with someone showing something on the laptop, is it meeting or work?

7) 008 vehicle you mean private car or any?

8) 010: being in a place with “sea” in his name is enough or it has to apparent sea on the image?

9) Are you going to give any ground truth examples? maybe this would answer some of the above questions

Thank you for your patience Ergina