Rescaling Egocentric Vision
This work provides a larger, more annotated dataset for egocentric vision research, addressing incremental improvements in data quality and scope for tasks like action recognition and detection.
The authors introduced EPIC-KITCHENS-100, an extended dataset of 100 hours with 20M frames and 90K actions, featuring denser and more complete annotations (54% more actions per minute and 128% more action segments) compared to its predecessor. This dataset enables new challenges like action detection and temporal generalization tests for models trained on older data.
This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics