SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03145 · ICCV · 2021

End-to-End Video Instance Segmentation via Spatial-Temporal Graph Neural Networks

Ning Xu, Weiyao Lin, Tao Wang, Kean Chen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Video instance segmentation is a challenging task that extends image instance segmentation to the video domain. Existing methods either rely only on single-frame information for the detection and segmentation subproblems or handle tracking as a separate post-processing step, which limit their capability to fully leverage and share useful spatialtemporal information for all the subproblems. In this paper, we propose a novel graph-neural-network (GNN) based method to handle the aforementioned limitation. Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking. Both inter and intra-frame information is effectively propagated and shared via graph updates and all the subproblems (i.e. detection, segmentation and tracking) are jointly optimized in an unified framework. The performance of our method shows great improvement on the YoutubeVIS validation dataset compared to existing methods and achieves 36.5% AP with a ResNet-50 backbone, operating at 22 FPS.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.03145")
get_code_for_paper("2203.03145")
have("2203.03145")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.03145.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.03145.svg)](https://syntology.ai/paper/2203.03145)

Connect an agent — have() is free.