AI Paper Atlas

Research map / Video / Video segmentation and tracking

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, Thomas Huang

ECCV 2018 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 646 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
add online learning (ablation)Ours · YouTube-VOS test (seen)J mean: 60.9 -> 66.9Improved
add online learning (ablation)Ours · DAVIS 2016 valmean IoU: 76.5 -> 79.1Improved
increase training data from 25% to 100% (ablation)Ours (w/o OL) · YouTube-VOS test (seen)J mean: 46.7 -> 60.9Improved
increase training data from 25% to 100% (ablation)Ours (w/o OL) · YouTube-VOS test (unseen)J mean: 40.1 -> 60.1Improved
add Initializer network (RGB frame plus mask) instead of using the mask as initial hidden state (ablation)Ours · YouTube-VOS test (seen)J mean: 45.1 -> 60.9Improved
add Initializer network instead of mask as hidden state (ablation)Ours · YouTube-VOS test (unseen)J mean: 38.6 -> 60.1Improved
feed previous predicted mask into Encoder (teacher forcing + curriculum) (ablation)Ours · YouTube-VOS test (seen)J mean: 60.9 -> 59.4No clear effect
feed previous predicted mask into Encoder (teacher forcing + curriculum) (ablation)Ours · YouTube-VOS test (unseen)J mean: 60.1 -> 60.7No clear effect
use pretrained DeepLab as Encoder instead of training on YouTube-VOS (ablation)Ours · DAVIS 2016 valmean IoU: 51.3 -> 45.6Hurt
add SegTrackv2, JumpCut and YoutubeObjects videos to 30 DAVIS training videos (ablation)Ours (from scratch) · DAVIS 2016 valmean IoU: 51.3 -> 51.9No clear effect
train on YouTube-VOS instead of DAVIS-scale dataOurs · DAVIS 2016 valmean IoU: 51.9 -> 76.5Improved

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