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

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Anticipation EPIC-KITCHENS-100 RU-LSTM Recall@5 13.94 # 6
Action Recognition EPIC-KITCHENS-100 TSM Action@1 37.39 # 24
Action Recognition EPIC-KITCHENS-100 TSN Action@1 33.57 # 29
Action Recognition EPIC-KITCHENS-100 SlowFast Action@1 36.81 # 25
Action Recognition EPIC-KITCHENS-100 TBN Action@1 35.55 # 27
Action Recognition EPIC-KITCHENS-100 TRN Action@1 35.28 # 28


No methods listed for this paper. Add relevant methods here