AI Paper Atlas

Research map / Video / Video segmentation and tracking

Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos

Bo Xiong, Suyog Dutt Jain, Kristen Lorraine Grauman

TPAMI 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 30 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 motion stream to appearance stream (joint model) (ablation)pixel objectness video model · DAVISAvg. IoU: 64.69 -> 72.82Improved
add appearance stream to motion stream (joint model) (ablation)pixel objectness video model · DAVISAvg. IoU: 60.18 -> 72.82Improved
add motion stream to appearance stream (joint model) (ablation)pixel objectness video model · YouTube-ObjectsAvg. IoU: 68.57 -> 68.95Improved
add appearance stream to motion stream (joint model) (ablation)pixel objectness video model · YouTube-ObjectsAvg. IoU: 49.43 -> 68.95Improved
add motion stream to appearance stream (joint model) (ablation)pixel objectness video model · SegTrack-v2Avg. IoU: 56.88 -> 64.44Improved
add appearance stream to motion stream (joint model) (ablation)pixel objectness video model · SegTrack-v2Avg. IoU: 53.04 -> 64.44Improved
learn motion model instead of thresholding optical flowvideo segmentation · DAVISAvg. IoU: 42.95 -> 60.18Improved
prune pseudo ground truth with bounding boxes (ablation)motion training data · 100 human-labeled framesJaccard: 70.2 -> 77.8Improved
evaluate on categories unseen in segmented training (Non-PASCAL)pixel objectness image model · ImageNet-LocalizationBBox-CorLoc: 62.12 -> 60.18No clear effect
use pixel objectness crop for retrieval instead of full imageVGG retrieval · ILSVRC2012 valmAP: 0.3082 -> 0.3342Improved
restrict to object-centric classes for retrievalpixel objectness retrieval · ILSVRC2012 first 400 classesmAP: 0.3342 -> 0.4166Improved
use pixel objectness instead of NLC on SegTrackvideo segmentation · SegTrack-v2Avg. IoU: 80 -> 64.44Hurt

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