The new competitions include
(i) Apparent Age Estimation in still images
(ii) Cultural Event Recognition (recognition of 100 categories in still images) on two novel datasets.
Competitions will be held via the Microsoft Codalab platform starting on June, 15th. More info will be posted soon at http://gesture.chalearn.org/
The results of the competitions and winner methods will be presented at ICCV 2015 ChaLearn LAP workshop, Chile, December 2015.
Prizes will include: economic prizes, travel grants, NVIDIA Tesla devices, winner certificate, and the possibility to publish your work at the workshop.
In addition best challenge and workshop papers will be invited to submit and extended version of their work to a high impact factor journal, special issue on Looking at People (SI under review at IJCV).
See below details of the competitions.
We would appreciate if you can share this information among your colleagues.
Special thanks to the sponsors of new challenging competitions in the field of Looking at People: Microsoft Research, Google, Facebook, Amazon, NVIDIA, Disney Research, IAPR TC-12, and European Cost action on Integrating Vision and Language.
ChaLearn organizes in 2015 two parallel challenge tracks on Apparent Age Estimation and Cultural Event Recognition. Data and details of the challenge tracks can be found at: http://gesture.chalearn.org/
The challenge features quantitative tracks to begin on June, 15th:
Track 1: Apparent Age Estimation: 5,000 images each displaying a single individual, labeled with the apparent age. Each image has been labeled by multiple individuals using a collaborative Facebook implementation. The votes variance is used as a measure of the error for the predictions. This is the first state of the art database for Apparent Age Recognition rather than Real Age recognition.
Track 2: Cultural Event Recognition: Near 30,000 images corresponding to 100 different cultural event categories will be considered. In all the categories, garments, human poses, objects and context will be possible cues to be exploited for recognizing the events, while preserving the inherent inter- and intra-class variability of this type of images. Examples of cultural events are Carnival, Oktoberfest, San Fermin, Maha-Kumbh-Mela, Aoi-Matsuri…
Prizes, for each Track:
1st winner: 1500 dollars, 1st winner certificate, 500 dollars travel grant, and NVIDIA Titan X device
2nd winner: 1000 dollars, 2nd winner certificate, 500 dollars travel grant, and NVIDIA Titan X device
3rd winner: 500 dollars, 3rd winner certificate, 500 dollars travel grant, and NVIDIA Titan X device
Important Dates for the Quantitative Participation:
June 15th, 2015: Beginning of the quantitative competition for Track 1 and for Track 2, release of development and validation data.
August 30th, 2015: Release of the encrypted final evaluation data and validation labels. Participants can start training their methods with the whole data set.
September 7th, 2015: Release of the decryption key for the final evaluation data. Participants can start predicting the results on the final evaluation labels. Deadline for code submission.
September 12th, 2015: End of the quantitative competition. Deadline for submitting the predictions over the final evaluation data. Deadline for code resubmission just if only small changes have been performed (no major changes). The organizers start the code verification by running it on the final evaluation data.
September 15th, 2015: Deadline for submitting the fact sheets.
September 19th, 2015: Release of the verification results to the participants for review. Top ranked participants are invited to follow the workshop submission guide for inclusion at ICCV 2015 ChaLearn Looking At People workshop proceedings.
September 27th, 2015: Workshop paper submission deadline, via the CMT LAP2015 workshop submission site.
October 10th, 2015: Notification of workshop paper acceptance.
October 15th, 2015: Camera ready of workshop papers.
December 12th, 2015: Workshop and awards session at ICCV 2015, Chile.
For more details please visit: http://gesture.chalearn.org/
Have a nice, challenging competition!