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
Cite
@article{arxiv.2209.13064,
title = {EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations},
author = {Ahmad Darkhalil and Dandan Shan and Bin Zhu and Jian Ma and Amlan Kar and Richard Higgins and Sanja Fidler and David Fouhey and Dima Damen},
journal= {arXiv preprint arXiv:2209.13064},
year = {2022}
}
Comments
10 pages main, 38 pages appendix. Accepted at NeurIPS 2022 Track on Datasets and Benchmarks Data, code and leaderboards from: http://epic-kitchens.github.io/VISOR