🔎 Elderly Action Recognition Challenge – WACV 2025
Are you ready to make a real-world impact with your AI models? Join us for the Elderly Action Recognition (EAR) Challenge, part of the Computer Vision for Smalls (CV4Smalls) Workshop at the WACV 2025 conference!
💡 Why Join?
This challenge is more than just a competition; it’s a mission to advance the recognition of the Activities of Daily Living (ADLs) for our senior population. Your innovations can improve safety and enhance quality of life, paving the way for groundbreaking advancements in computer vision.
🎯 Your Objective
Start with a general human action recognition benchmark and fine-tune your models on a specialized dataset of elderly-specific activities using transfer learning. Show us your robust, adaptable, and scalable solutions in real-world scenarios!
👣 Next Steps
Dive into the dataset, curate your training set, and refine your approach.
Start experimenting with model architectures and techniques like transfer learning.
📂 Training Dataset
The training datasets are available on multiple websites. You’ll need access to those. Here are the links:
These datasets are your starting point for curating high-quality data using FiftyOne (https://docs.voxel51.com/). Then, you can start the training process.
📆 Submission Deadline
The evaluation dataset will be released on January 31st. It will allow you to test your models on unseen data. Stay tuned!
Deadline: February 15th, 2025.
👥 Who Can Participate?
Everyone is welcome, whether you’re from academia, industry, or a student passionate about advancing AI for the societal good.
Proudly sponsored by Voxel51, this is your chance to innovate, collaborate, and make a difference. Let’s come together to improve care for older adults using cutting-edge AI solutions!
🎙️ Good Listens
🗓️. Upcoming In-Person Events
Check out these upcoming In-Person AI, machine learning and computer vision events! View the full calendar and register for an event.
🗓️. Upcoming Virtual Events
Check out these upcoming Virtual AI, machine learning and computer vision events! View the full calendar and register for an event.