SOTAVerified

Scene Parsing

Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. MIT Description

Papers

Showing 191199 of 199 papers

TitleStatusHype
Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRFCode0
Dual-Glance Model for Deciphering Social RelationshipsCode0
DeLS-3D: Deep Localization and Segmentation with a 3D Semantic MapCode0
Semantic Understanding of Scenes through the ADE20K DatasetCode0
SalientDSO: Bringing Attention to Direct Sparse OdometryCode0
Adaptive Pyramid Context Network for Semantic SegmentationCode0
Boosting Real-Time Driving Scene Parsing with Shared SemanticsCode0
Complete 3D Scene Parsing from an RGBD ImageCode0
SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV ApplicationsCode0
Show:102550
← PrevPage 20 of 20Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PGDPNetTotal Accuracy84.7Unverified
2Inter-GPSTotal Accuracy27.3Unverified
#ModelMetricClaimedVerifiedStatus
1VCD No CoarsemIoU82.3Unverified