ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios
This dataset enables systematic study of human behavior in industrial settings, addressing a domain-specific need for fine-grained understanding of human-object interactions.
The authors introduced ENIGMA-51, a new egocentric dataset with 51 video sequences from industrial repair scenarios, densely annotated for human behavior analysis, and provided baseline results showing it poses a challenging benchmark for tasks like human-object interaction detection and anticipation.
ENIGMA-51 is a new egocentric dataset acquired in an industrial scenario by 19 subjects who followed instructions to complete the repair of electrical boards using industrial tools (e.g., electric screwdriver) and equipments (e.g., oscilloscope). The 51 egocentric video sequences are densely annotated with a rich set of labels that enable the systematic study of human behavior in the industrial domain. We provide benchmarks on four tasks related to human behavior: 1) untrimmed temporal detection of human-object interactions, 2) egocentric human-object interaction detection, 3) short-term object interaction anticipation and 4) natural language understanding of intents and entities. Baseline results show that the ENIGMA-51 dataset poses a challenging benchmark to study human behavior in industrial scenarios. We publicly release the dataset at https://iplab.dmi.unict.it/ENIGMA-51.