In this challenge, participants will create methods for recognizing 12 activities conducted by nurses in both lab and in real-life settings. In real world, there is high chance of getting missing labels during experiments since users are busy at work. The main challenge is leveraging laboratory data to improve models in real-life. Training data consists of data collected in both settings but test data consists of data only from the real field (same users as training data).
All participants may use the data free of charge.
Submissions will be evaluated by the Accuracy using following formula:
The winner (one team representative) will be invited to our installations in Kitakyushu, Japan.
Challenge is open to students, graduate students, researchers, professors, and data scientists. Members of Sozolab (“Organizers”) are not eligible to enter or win. To be eligible, participants need to register in the challenge, submit their results and a paper to HASCA Workshop. Only submissions with a submitted paper are eligible to win a prize.
All participants are encouraged to participate in the Workshop to share details about their approach.
Previously Organized Challenges