Multimodal Emotion Recognition Challenge by Neurodata Lab
Hello! Our laboratory Neurodata Lab launches in October and November 2017 ML-own contest to recognize emotions.
→ Competition site
The competition itself, called the Multimodal Emotion Recognition Challenge (MERC 2017) , will be held in an online format.
At this stage, the goal is to recognize the basic human emotions in the video through four channels - face, voice, eyes, body - through which the required signs are counted (which we will tell you more about at the start of the competition). The main emphasis is on the fact that some data remains inaccessible, which means that you need to learn how to make a correct prediction in such conditions (about 30% of the data in the sample are missing - they are replaced by zeros).
Output: 6 emotions. Each person is marked with annotators according to what emotion he is experiencing at a given moment in time. An agreement score will also be available on the training set, calculated as the ratio of the “for” marks to the most frequent emotion (it is always the same) to the total number of marks put by several annotators.
We have a leaderboard. It is formed according to the unweighted accuracy metric. In more detail - again after the official launch. In addition to the total prize pool ($ 3,500.00), the jury retains the right to note the decisions that they liked based on three criteria: accuracy, universality, and innovativeness.
This is the first of a series of our initiatives (competitive and grant), designed to gradually and with increasing complexity step by step introduce the broad issues of Emotion AI (emotional AI, as the direction of “emotional research and technology” is increasingly called) into the current context of reflection, analysis and development of the Russian-speaking (and not only) community of specialists in Data Science, ML and CV.
Pre-registration is open on October 6th.
Access to the materials will be provided on October 18, 2017.
Summing up and announcing the winners are expected on November 28, 2017. The
jury of the competition includes experts from Skoltech-IPPI RAS and NRU ITMO, the project is provided with information and consulting support by colleagues from MIPT, VMK Moscow State University and Milan Polytechnic University (Politecnico di Milano).
Join now! And success!
→ Competition site
The competition itself, called the Multimodal Emotion Recognition Challenge (MERC 2017) , will be held in an online format.
At this stage, the goal is to recognize the basic human emotions in the video through four channels - face, voice, eyes, body - through which the required signs are counted (which we will tell you more about at the start of the competition). The main emphasis is on the fact that some data remains inaccessible, which means that you need to learn how to make a correct prediction in such conditions (about 30% of the data in the sample are missing - they are replaced by zeros).
Output: 6 emotions. Each person is marked with annotators according to what emotion he is experiencing at a given moment in time. An agreement score will also be available on the training set, calculated as the ratio of the “for” marks to the most frequent emotion (it is always the same) to the total number of marks put by several annotators.
We have a leaderboard. It is formed according to the unweighted accuracy metric. In more detail - again after the official launch. In addition to the total prize pool ($ 3,500.00), the jury retains the right to note the decisions that they liked based on three criteria: accuracy, universality, and innovativeness.
This is the first of a series of our initiatives (competitive and grant), designed to gradually and with increasing complexity step by step introduce the broad issues of Emotion AI (emotional AI, as the direction of “emotional research and technology” is increasingly called) into the current context of reflection, analysis and development of the Russian-speaking (and not only) community of specialists in Data Science, ML and CV.
Pre-registration is open on October 6th.
Access to the materials will be provided on October 18, 2017.
Summing up and announcing the winners are expected on November 28, 2017. The
jury of the competition includes experts from Skoltech-IPPI RAS and NRU ITMO, the project is provided with information and consulting support by colleagues from MIPT, VMK Moscow State University and Milan Polytechnic University (Politecnico di Milano).
Join now! And success!