AI Paper Atlas

Research map / Video / Video segmentation and tracking

Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos

Mingze Xu, Chenyou Fan, Yuchen Wang, Michael S. Ryoo, David J. Crandall

ECCV 2018 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 39 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 optical flow stream to image stream (ablation)two-stream joint FCN · IU ShareView third-thirdIoU: 49.3 -> 62.7Improved
add optical flow stream to image stream (ablation)two-stream joint FCN · IU ShareView third-firstACC: 52.7 -> 73.1Improved
add image stream to optical flow stream (ablation)two-stream joint FCN · IU ShareView third-firstmAP: 55.1 -> 65.2Improved
add soft attention re-weighting of features (ablation)third-third joint model · IU ShareView third-thirdACC: 48.9 -> 55.5Improved
add soft attention re-weighting of features (ablation)third-first joint model · IU ShareView third-firstACC: 61.7 -> 73.1Improved
add soft attention re-weighting of features (ablation)third-first joint model · UTokyo Ego-SurfACC: 44.0 -> 55.2Improved
add soft attention re-weighting of features (ablation)third-third joint model · UTokyo Ego-SurfACC: 36.7 -> 42.0Improved
add soft attention re-weighting of features (ablation)third-third joint model · IU ShareView third-thirdIoU: 60.6 -> 62.7Improved
replace ground-truth bounding-box cropping with soft attention from predicted segmentationjoint model · IU ShareView third-thirdmAP: 44.2 -> 49.0Improved
replace ground-truth bounding-box cropping with soft attention from predicted segmentationjoint model · IU ShareView third-firstmAP: 64.1 -> 65.2Improved
jointly learn matching with segmentation instead of segmentation onlytwo-stream FCN · IU ShareView third-thirdIoU: 57.3 -> 62.7Improved
jointly learn matching with segmentation instead of segmentation onlytwo-stream FCN · IU ShareView third-firstIoU: 57.3 -> 61.9Improved

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