ChaLearn Looking at People


About us


Looking at People (LAP) is a challenging area of research that deals with the problem of recognizing people in images, their posture, performing action/gesture recognition from still images or image sequences, also considering multi-modal data, among others. Any scenario where the visual or multi-modal analysis of people takes place is of interest within the field of Looking at People. Several subareas of LAP have been recently defined, such as Affective Computing, Social Signal Processing, Human Behavior Analysis, Personality Computing or Social Robotics. The effort involved in this area of research will be compensated by its potential applications for good: TV production, home entertainment (multimedia content analysis), education purposes, sociology research, surveillance and security, improved quality life by means of monitoring or automatic artificial assistance, support to early diagnosis and intervention in mental diseases, etc.

This page summarizes all previous, current, and upcoming events organized by the ChaLearn LAP team, including international workshops, competitions, special issues, books and other publications related to ChaLearn LAP events. Associated databases and their state-of-the-art results are also available. We would like to thank all the hundreds of participants that joined our events and that considerably help to advance in both theory and practice of LAP. We thank all of our collaborators that help to advance in the research of LAP from the required multi-disciplinary perspective. We thank our sponsors, including Microsoft Research, Google, NVIDIA Corportation, Disney Research, Facebook, and Amazon, among others.



Despite all of the efforts devoted to the compilation and curation of resources available in this website, we cannot guarantee that collected data including associated annotations and labels (obtained through manually, automatically and a semi-automatically processes) are representative samples of a real application scenario. The adopted data gathering and labeling methodologies may not include exhaustive and/or inclusive mechanisms that allow users to reach conclusive findings. More importantly, we strongly advise users NOT using the resources available in this site to build systems that make decisions and recommendations that have a direct or indirect impact into people's lives. Likewise, we acknowledge and apologize for those resources and publications available in this site may use ambiguous terms (e.g., gender vs. sex or ethnicity vs. race), we have not deliberately aimed to cause controversy or affect users in any form.


ChaLearn LAP datasets license


The ownership of ChaLearn LAP datasets, if no other information is provided at each specific dataset webpage, belongs to their authors. They are licensed under Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)


ChaLearn LAP datasets, if no other information is provided at each specific dataset webpage, are presented "AS IS". By downloading and using them, you acknowledge they may contain errors, and take full responsibility on any potential risk or damage. To the fullest extent provided by law, in no event will we, our affiliates, or our licensors, service providers, employees, agents, officers, or directors be liable for damages of any kind, under any legal theory, arising out of or in connection with the developer’s use, or inability to use, the services, datasets, any content on the services or such other services, including any direct, indirect, special, incidental, consequential, or punitive damages, including but not limited to, personal injury, pain and suffering, emotional distress, loss of revenue, loss of profits, loss of business or anticipated savings, loss of use, loss of goodwill, loss of data, and whether caused by tort (including negligence), breach of contract, or otherwise, even if foreseeable.


CVPR 2021 Challenge

The ChaLearn Looking at People RGB and RGBD Sign Language Recognition Challenge webpage has been released.

ECCV'20 FairFaceRec Challenge

Thanks to our sponsor (anyvision), we are going to have some prizes for top winning solutions:
1st place 1000 €
2nd place 500 €
3rd place 500 €

100% online

ECCV 2020 is going ahead and will be a 100% online event. Technically, a unified platform is being decided by ECCV organizers and will be communicated soon.

Coronavirus information.

FG2020 Posponed

Dear FG community,

IEEE has been monitoring the developing Coronavirus outbreak.

The safety and well-being of all conference participants is our priority. After studying and evaluating the announcements, guidance, and news released by relevant national departments, we are sorry to announce that IEEE FG 2020, scheduled to be held 18-22th May/Buenos Aires will be postponed to a later date.

We have tentatively rescheduled FG2020 for 16 to 20 November. We remain committed to hosting IEEE FG 2020 in Buenos Aires. In the unfortunate case that that proves impossible, we are considering a virtual conference. The conference proceedings and registration will be delayed. We will report back to you about the proceedings once more is known.

Again, we apologize for any inconvenience this has caused and please contact


FG 2020 chairs

ECCV 2020

ChaLearn Looking at People workshop on Fair Face Recognition and Analysis and associated Challenge.