|
|
|
|
|
|
|
|
|
|
|
|
|
|
| We introduce a new egocentric dataset called Human Kitchen Interactions (HKI) to investigate the synth-to-real gap. Our dataset contains in total 100 synthetic and real videos in which 21 different actions are executed in a kitchen environment. The synthetic data is acquired in an egocentric virtual reality (VR) setup while capturing the virtual environment in a game engine. Additionally, we evaluate state-of-the-art online action detection models on our dataset, provide insights into synth-to-real domain shift and investigate how far models trained on synthetic data can generalize to real data. |
|
|
|