FudanCVL/MeViSv2 download history

FudanCVL/MeViSv2 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,379 times (380 in the last 7 days), and 6,317 times in total. It ranks #15,170 among datasets by monthly downloads.

MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation ๐Ÿ [Project page]โ€ƒ ๐Ÿ“„[arXiv] โ€ƒ ๐Ÿ’พ[Evaluation Server v1 (legacy)]โ€ƒ ๐Ÿ”ฅ[Evaluation Server v2] This repository contains code for ICCV2023 and TPAMI 2025 paper: MeViS: A Multi-Modal Dataset for Referring Motion Express

Open FudanCVL/MeViSv2 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.