2016 Looking at People ECCV Challenge

Congratulations to the winners!

Overview paper:

[DOWNLOAD DRAFT]

* Victor Ponce Lopez, Baiyu Chen, Albert Places, Marc Oliu, Ciprian Corneanu, Xavier Baro, Hugo Jair Escalante, Isabelle Guyon, Sergio Escalera. ChaLearn LAP 2016: First Round Challenge on First Impressions - Dataset and Results. ChaLearn Looking at People Workshop on Apparent Personality Analysis, ECCV Workshop proceedings, LNCS, Springer, 2016, in press.

Winners:

* 1st place.

Chen-Lin Zhang, Hao Zhang, Xiu-Shen Wei and Jianxin Wu. Deep Bimodal Regression for Apparent Personality Analysis. ChaLearn Looking at People Workshop on Apparent Personality Analysis, ECCV Workshop proceedings, LNCS, Springer, 2016, in press.

* 2nd place.

Arulkumar Subramaniam, Vismay Patel, Ashish Mishra, Prashanth Balasubramanian, Anurag Mittal. Bi-modal First Impressions Recognition usingTemporally Ordered Deep Audio and StochasticVisual Features. ChaLearn Looking at People Workshop on Apparent Personality Analysis, ECCV Workshop proceedings, LNCS, Springer, 2016, in press.

* 3rd place, in press.

Yağmur Güçlütürk, Umut Güçlü, Marcel van Gerven, Rob van Lier. Deep Impression: Audiovisual Deep Residual Networks for Multimodal Apparent Personality Trait Recognition. ChaLearn Looking at People Workshop on Apparent Personality Analysis, ECCV Workshop proceedings, LNCS, Springer, 2016, in press.

ChaLearn Looking at People Workshop on Apparent Personality Analysis and

First Impressions Challenge @ ECCV2016

Workshop and Challenge on Apparent Personality Analysis

University of Amsterdam, Amsterdam, Netherlands

9th October, 2016

ChaLearn organizes for ECCV2016 Workshop on Apparent Personality Analysis and a quantitative challenge on First Impressions recognition. The proposed workshop aims at studying all aspects of computer vision and pattern recognition devoted to the analysis of human personality from images and videos. Co-located with the workshop there is a challenge on first impressions, that is, recognizing personality traits for users after seeing a short video.

Workshop/challenge participants will be invited to submit revised and extended versions of their papers to be considered for publication in a

Special Issue on Personality Analysis in the IEEE Transactions on Affecfive Computing

Please refer to the SI site for more details.

Workshop on Apparent Personality Analysis: Personality refers to individual differences in characteristic patterns of thinking, feeling and behaving. Characterizing personality automatically from video analysis is far from being a trivial task because perceiving personality traits is not easy even to humans, unless they are professionally trained (psychologists, recruiting specialists). Additionally, many personality traits are not precisely defined and there is no consensus among psychologists about how to capture them accurately, e.g. via standardized tests. We are organizing a workshop that will compile state of the art on all areas of automatic analysis of personality from a computer vision perspective.

Preliminary workshop program:

NEWS

March 23: Final results for Track 1 (Apparent Age Estimation) are now available. Thank you all for participating, we wish you enjoyed the challenge!

January 25: Tracks 1 (Apparent Age Estimation), 2 (Accessories Classification) and 3 (Smile and Gender Classification) started. Enjoy the Challenge!

Important dates (Workshop):

Extended deadlines:

  • End of ECCV first impressions challenge July 13,
  • Paper submission deadline for ECCVW July 25
  • Notification of acceptance to ECCVW authors August, 8
  • Submission deadline ICPRW (no participants) August, 10
  • End of ICPR competition August, 16
  • Submission deadline ICPRW
  • (contest participants & ECCV revised-rejected papers August 24
  • Notification of acceptance ICPRW (no participants): August 24
  • Notification of acceptance ICPRW
  • (contest participants & ECCV revised-rejected papers) September, 2
  • Camera ready submission ECCV September, 2
  • Camera ready submission ICPR September, 5
  • Workshop and awards session at ECCV2016, October 9

Please refer to the workshop section for more details.

First impressions challenge

Co-located with the workshop we are organizing a challenge on “first impressions”, in which participants will develop solutions for recognizing personality traits of users in short video sequences. We will make available a large newly collected data set sponsored by Microsoft of at least 10,000 15-second videos collected from YouTube, annotated with personality traits by AMT workers. The traits will correspond to the “big five” personality traits used in psychology and well known of hiring managers using standardized personality profiling: Extroversion, agreeableness, conscientiousness, neuroticism, and openness to experience. As is known, the first impression made is highly important in many contexts, such as human resourcing or job interviews. This work could become very relevant to training young people to present themselves better by changing their behavior in simple ways. The participants who obtain the best results in the challenge will be invited to submit a paper to the workshop.

Please refer to the data and description section for more details.

Table 1. Sample videos that will be used for the first impression challenge.

Top three ranked participants of the challenge will receive a prize as follows (estimated, it depends on the available budget):

    • First place: 1500USD + 400USD travel grant + award certificate
  • Second place: 1000USD + 400USD travel grant + award certificate
  • Thrid- place: 500USD + 400USD travel grant + award certificate

in addition top ranked participants will be invited to follow the workshop submission guide for inclusion of a description of their system at the ECCV 2016 workshop proceedings, participants of the workshop or challenge will be invited to submit revised and extended versions of their papers to be considered for publication in a special issue on personality analysis in the IEEE Transactions on Affecfive Computing.

Important dates (quantitative challenge):

  • May, 15th, 2016: Beginning of the quantitative competition, release of development (with labels) and validation data (without labels).
  • June 30th, 2016: Release of encrypted final evaluation data (without labels) and validation labels. Participants can start training their methods with the whole data set.
  • July 3rd, 2016: Release of final evaluation data decryption key. Participants start predicting the results on the final evaluation data.
  • July 13th, 2016: End of the quantitative competition. Deadline for submitting the predictions over the final evaluation data. Deadline for code submission. The organizers start the code verification by running it on the final evaluation data.
  • July 15th, 2016: Deadline for submitting the fact sheets.
  • July 15th, 2016: Release of the verification results to the participants for review. Top ranked participants are invited to follow the workshop submission guide for inclusion at ECCV 2016 ChaLearn Looking at People workshop proceedings.

Winners for the first round competition @ ECCV:

1st: Team NJU-LAMDA

2nd: Team evolgen

3rd: Team DCC

Winners for the second round coopetition @ ICPR:

1st: Team BU-NKU

2nd: Team evolgen

3rd: Team pandora

Papers:

ChaLearn LAP 2016: First Round Challenge on First Impressions - Dataset and Results. V. Ponce-López, B. Chen, M. Oliu, C. Cornearu, A. Clapés, I. Guyon, X. Baró, H.J. Escalante, S. Escalera. ECCV 2016, In press.

We are very grateful with our sponsors:

Microsoft
Chalearn

Thanks to our ECCV 2016 sponsors: Microsoft Research, ChaLearn, University of Barcelona, INAOE, NVIDIA corporation, more TBA. This research has been partially supported by projects TIN2012-39051 and TIN2013-43478-P.