Scaling Egocentric Vision: The Dataset

By Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price and 1 more. 2018

72 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, methodology): “In this paper, we present EPIC-KITCHENS-100, an egocentric video dataset that extends our previous dataset [1] to 100 hours, capturing diverse unscripted and unedited human-object interactions in people’s kitchens.”
Long-Term Feature Banks for Detailed Video Understanding (2018, methodology): “ns. 51.9 81.2 27.8 52.5 20.5 39.4 LFB NL 52.4 80.8 29.3 54.9 20.8 39.8 LFB Avg 53.2 81.6 29.8 55.9 20.9 40.9 LFB Max 54.4 81.8 32.1 57.5 23.3 42.2 +4.6 +1.2 +6.0 +6.2 +4.3 +4.4 Test s1 (seen) TSN RGB [6] 45.7 85.6 36.8 64.2 19.9 41.9 TSN Flow [6] 42.8 79.5 17.4 39.4 9.0 21.9 TSN Fusion [6] 48.2 84.1”
A Survey on Food Computing (2018, methodology): “Besides food images, [Damen et al. 2018] used the head-mounted GoPro to record the cooking videos.”
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities (2020, background): “Conversely, instructional video datasets [1,54,32,31,46] tackle goal-directed multi-step tasks, mostly in cooking, repairing, and assembling activities.”
Learning to Learn Words from Visual Scenes (2019, methodology): “We evaluate our approach on two established datasets, Flickr30k [63] and EPIC-Kitchens [8], both of which have a large diversity of natural scenes and a long-tail word distribution.”
Efficient Object Annotation via Speaking and Pointing (2019, methodology): “(Damen et al. 2018) annotates the EPIC-KITCHENS dataset based on spoken free-form narratives, which cover some of the objects present in the image.”
Self-Supervised Learning by Cross-Modal Audio-Video Clustering (2019, background): “ition of suitable label spaces for action recognition. Recent video datasets differ substantially in their label spaces, which range from sports actions [24] to verb-noun pairs for kitchen activities [5]. This suggests that the deﬁnition of the “right” label space for action recognition, and more ge”