SOTAVerified

Scene Understanding

Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1251–1275 of 1723 papers

TitleStatusHype
Bridging Scene Understanding and Task Execution with Flexible Simulation Environments—0
RELLIS-3D Dataset: Data, Benchmarks and AnalysisCode1
SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple EnvironmentsCode1
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition—0
Towards Efficient Scene Understanding via Squeeze ReasoningCode1
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingCode2
S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation—0
Learning Regional Purity for Instance Segmentation on 3D Point CloudsCode0
Highway Driving Dataset for Semantic Video Segmentation—0
Real-time Semantic Segmentation with Context Aggregation Network—0
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds—0
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic SegmentationCode1
Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce ModelCode1
Axiom Learning and Belief Tracing for Transparent Decision Making in Robotics—0
RADIATE: A Radar Dataset for Automotive Perception in Bad WeatherCode1
Unsupervised Foveal Vision Neural Networks with Top-Down Attention—0
Learning Panoptic Segmentation from Instance ContoursCode0
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM—0
Constructing a Visual Relationship Authenticity DatasetCode0
Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer—0
ALFWorld: Aligning Text and Embodied Environments for Interactive LearningCode1
Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors—0
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph ConsensusCode0
MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene UnderstandingCode1
Semi-Supervised Learning of Multi-Object 3D Scene Representations—0
Show:102550
← PrevPage 51 of 69Next →
All datasetsSemantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K valSemantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.44—Unverified
2Team VGAI (TCS Research)OMQ0.37—Unverified
3Demo_semantic_SLAMOMQ0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1CPN(ResNet-101)Mean IoU46.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.35—Unverified