Skip to yearly menu bar Skip to main content


EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

Ahmad Darkhalil · Dandan Shan · Bin Zhu · Jian Ma · Amlan Kar · Richard Higgins · Sanja Fidler · David Fouhey · Dima Damen

Hall J (level 1) #1026

Keywords: [ Action ] [ Active Objects ] [ Pixel Segmentations ] [ Egocentric Vision ] [ Long-Term Understanding ] [ Hands ]


We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning.For data, code and leaderboards:

Chat is not available.