AI Paper Atlas

Research map / Video / Video segmentation and tracking

Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision

Weijian Jian, Xiaoyue Zhang, Bin Xiao, Chunyu Xie, Yixiao He, Yutao Liu, Dawei Leng, Yuhui Yin

ECCV 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 0 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 PGCL loss instead of BCE+Dice (ablation)PGM · SA-1B 1000 imagesAR (%): 3.8 -> 28.3Improved
add PGCL loss instead of Slot Attention (ablation)PGM · SA-1B 1000 imagesAR (%): 8.2 -> 28.3Improved
add MFSM to ROSM (ablation)MGMS pipeline · SA-1B 1000 imagesAR (%): 28.8 -> 36.6Improved
add ROSM to MFSM (ablation)MGMS pipeline · SA-1B 1000 imagesAR (%): 34.7 -> 36.6Improved
combine maskness and boundary sharpness scores (ablation)MGMS mask filtering · Whole-image AvgAR (%): 24.1 -> 28.8Improved
combine maskness with sharpness versus sharpness alone (ablation)MGMS mask filtering · Whole-image AvgAR (%): 22.8 -> 28.8Improved
increase prediction heads from one to four (ablation)PGM · SA-1B 1000 imagesAR (%): 27.9 -> 36.6Improved
increase prediction heads from four to five (ablation)PGM · SA-1B 1000 imagesAR (%): 36.6 -> 36.5No clear effect
increase video pre-training data from 100h to 1,000h (ablation)PGM · SA-1B 1000 imagesAR (%): 16.8 -> 28.3Improved
increase video pre-training data from 1,000h to 10,000h (ablation)PGM · SA-1B 1000 imagesAR (%): 28.3 -> 36.6Improved
add CRF refinement to PGM pseudo-masksPGM · Whole-image AvgAR (%): 28.8 -> 30.1Improved
use PGM unrefined masks instead of UnSAM CascadePSP pseudo-labelsPGM · Whole-image AvgAR (%): 21.7 -> 28.8Improved

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