LOMM
Official code for Latest Object Memory Management for Temporally Consistent Video Instance Segmentation
Install / Use
/learn @Seung-Hun-Lee/LOMMREADME
LOMM (ICCV 2025)
Latest Object Memory Management for Temporally Consistent Video Instance Segmentation Paper | Project
<img src="https://github.com/Seung-Hun-Lee/LOMM/blob/main/assets/LOMM_ICCV_2025.png" width="800"/> </div>News
- We release our code with trained models
2025.09.17 - Our paper has also been accepted to MemVis: The 1st Workshop on Memory and Vision at ICCV 2025
2025.08.30
Data preparation & Installation
See Datasets & Installation
Getting Started
Model Zoo
We provide our trained models here
Citation
@article{lee2025latest,
title={Latest Object Memory Management for Temporally Consistent Video Instance Segmentation},
author={Lee, Seunghun and Seo, Jiwan and Choi, Minwoo and Han, Kiljoon and Jeong, Jaehoon and Durante, Zane and Adeli, Ehsan and Park, Sang Hyun and Im, Sunghoon},
journal={arXiv preprint arXiv:2507.19754},
year={2025}
}
Related Skills
qqbot-channel
347.2kQQ 频道管理技能。查询频道列表、子频道、成员、发帖、公告、日程等操作。使用 qqbot_channel_api 工具代理 QQ 开放平台 HTTP 接口，自动处理 Token 鉴权。当用户需要查看频道、管理子频道、查询成员、发布帖子/公告/日程时使用。
docs-writer
100.1k`docs-writer` skill instructions As an expert technical writer and editor for the Gemini CLI project, you produce accurate, clear, and consistent documentation. When asked to write, edit, or revie
model-usage
347.2kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Design
Campus Second-Hand Trading Platform \- General Design Document (v5.0 \- React Architecture \- Complete Final Version)1\. System Overall Design 1.1. Project Overview This project aims t
