ActionVOS: Actions as Prompts for Video Object Segmentation
Our paper is accepted by ECCV-2024
Picture: Overview of the proposed ActionVOS setting
Picture: The proposed method in our paper.
This repository contains the official PyTorch implementation of the following paper:
ActionVOS: Actions as Prompts for Video Object Segmentation
Liangyang Ouyang, Ruicong Liu, Yifei Huang, Ryosuke Furuta, and Yoichi Sato
Abstract:
Material related to our paper is available via the following links:
- Paper:
- Code: https://github.com/ut-vision/ActionVOS
- VISOR dataset: https://epic-kitchens.github.io/VISOR/
- VOST dataset: https://www.vostdataset.org/data.html
- VSCOS dataset: https://github.com/venom12138/VSCOS
- ReferFormer Model: https://github.com/wjn922/ReferFormer
- Our experiment is tested with Python 3.8, PyTorch 1.11.0.
If this work or code is helpful in your research, please cite:
For any questions, including algorithms and datasets, feel free to contact me by email: oyly(at)iis.u-tokyo.ac.jp