EatSense: Human Centric, Action Recognition and Localization Dataset for Understanding Eating Behaviors and Quality of Motion Assessment

We introduce a new benchmark dataset named EatSense that targets both computer vision and the healthcare community. EatSense is recorded while a person eats in a dining room uncontrolled setting. Key features are: First, it introduces challenging atomic actions for recognition. Second, the hugely varying lengths of actions in EatSense, make it nearly impossible for current temporal action localization frameworks to localize them. Third, it provides the capability to model complete eating behaviour (chain of action-based). Lastly, it simulates minor changes in motion/performance. Moreover, we conduct extensive experiments on EatSense with baseline deep learning-based approaches for bench-marking and hand-crafted feature-based approaches for explainable applications. We believe this dataset will benefit future researchers in building robust temporal action localization networks, behaviour recognition and performance assessment models for eating. The dataset is related to the publication by Muhammad Ahmed Raza, Longfei Chen, Nanbo Li and Robert B. Fisher (2023). "EatSense: Human centric, action recognition and localization dataset for understanding eating behaviors and quality of motion assessment", Image and Vision Computing, 137, 104762, ISSN 0262-8856, https://doi.org/10.1016/j.imavis.2023.104762