EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

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

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

TL;DR: New dataset and benchmark suite for long-term pixel-level segmentations of hand-object interactions in egocentric video

Abstract:

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: http://epic-kitchens.github.io/VISOR

Author Statement: Yes

URL: https://epic-kitchens.github.io/VISOR/

Dataset Url: https://epic-kitchens.github.io/VISOR/

License: CC BY-NC 4.0 license

Contribution Process Agreement: Yes

In Person Attendance: Yes

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:2209.13064/code)