First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Datasets


Introduced in the Paper:

EPIC-KITCHENS-55

Used in the Paper:

Charades Breakfast Charades-Ego
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Anticipation EPIC-KITCHENS-55 (Seen test set (S1)) ATSN Top 1 Accuracy - Verb 31.81 # 5
Top 1 Accuracy - Noun 16.22 # 5
Top 1 Accuracy - Act. 6.00 # 6
Top 5 Accuracy - Verb 76.56 # 5
Top 5 Accuracy - Noun 42.15 # 5
Top 5 Accuracy - Act. 28.21 # 5
Action Anticipation EPIC-KITCHENS-55 (Seen test set (S1)) 2SCNN Top 1 Accuracy - Verb 29.76 # 6
Top 1 Accuracy - Noun 15.15 # 7
Top 1 Accuracy - Act. 4.32 # 7
Top 5 Accuracy - Verb 76.03 # 6
Top 5 Accuracy - Noun 38.56 # 7
Top 5 Accuracy - Act. 15.21 # 7
Action Anticipation EPIC-KITCHENS-55 (Unseen test set (S2) ATSN Top 1 Accuracy - Verb 25.30 # 5
Top 1 Accuracy - Noun 10.41 # 5
Top 1 Accuracy - Act. 2.39 # 6
Top 5 Accuracy - Verb 68.32 # 6
Top 5 Accuracy - Noun 29.50 # 5
Top 5 Accuracy - Act. 6.63 # 7
Action Anticipation EPIC-KITCHENS-55 (Unseen test set (S2) 2SCNN Top 1 Accuracy - Verb 25.23 # 6
Top 1 Accuracy - Noun 9.97 # 6
Top 1 Accuracy - Act. 2.29 # 7
Top 5 Accuracy - Verb 68.66 # 5
Top 5 Accuracy - Noun 27.38 # 6
Top 5 Accuracy - Act. 9.35 # 5

Methods


No methods listed for this paper. Add relevant methods here