AI Paper Atlas

Research map / Video / Video segmentation and tracking

Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation

Xiangtai Li, Haobo Yuan, Wenwei Zhang, Guangliang Cheng, Jiangmiao Pang, Chen Change Loy

ICCV 2023 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use tube matching (2-frame subclip) instead of frame matching in the Mask2Former-VIS+ baseline (ablation)Mask2Former-VIS+ · VIPSeg val (ResNet50)VPQ: 32.4 -> 34.5Improved
add cross-tube temporal contrastive learning (TCL) (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 34.5 -> 36.8Improved
add cross-tube linking (CTL) on top of TCL (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 36.8 -> 37.5Improved
replace tube-mask association targets with single-frame GT masks (ablation)Tube-Link TCL · VIPSeg val (ResNet50)VPQ: 37.5 -> 35.6Hurt
use global query matching rather than dense or sparse query matching for contrastive learning (ablation)Tube-Link TCL · VIPSeg val (ResNet50)VPQ: 34.5 -> 37.5 vs sparse query; 30.2 -> 37.5 vs denseImproved
increase training subclip size from 1 to 2 (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 35.6 -> 37.5Improved
increase training subclip size from 2 to 3 or add frame overlap (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 37.5 -> 37.0 (T=3); 37.3 (overlap)No clear effect
enlarge inference window from 2 to 6 (trained with 2) (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 37.5 -> 39.2Improved
enlarge inference window further to 8 (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 39.2 -> 38.5Hurt
use learned tube embedding for tracking instead of extra tracker, RoI features or query embedding (ablation)Tube-Link · VIPSeg val (ResNet50)VPQ: 36.6 -> 37.5 vs extra trackerImproved
feed two-frame subclips to pretrained Min-VIS and Video K-Net without retrainingMin-VIS / Video K-Net · YouTube-VIS-2019 / VIPSegmAP / VPQ: 47.4 -> 48.8 (Min-VIS YTVIS19); 26.1 -> 27.6 (Video K-Net VIPSeg)Improved
Tube-Link versus TubeFormer on VSPW semantic segmentationTube-Link Swin-large · VSPW-VSS valmIoU: 59.7 vs 63.2 (TubeFormer)Hurt

Later papers that compared with this method

2 later accepted papers report Tube-Link as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy