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 1501–1525 of 1723 papers

TitleStatusHype
Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic SegmentationCode0
A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM—0
Context-Dependent Diffusion Network for Visual Relationship Detection—0
Answering Visual What-If Questions: From Actions to Predicted Scene Descriptions—0
On the Importance of Visual Context for Data Augmentation in Scene Understanding—0
Modeling human intuitions about liquid flow with particle-based simulation—0
Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?Code0
BOLD5000: A public fMRI dataset of 5000 imagesCode0
Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene ImagesCode0
Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video—0
Localization Guided Learning for Pedestrian Attribute Recognition—0
Single Shot Scene Text RetrievalCode0
COFGA: Classification Of Fine-Grained Features In Aerial Images—0
NavigationNet: A Large-scale Interactive Indoor Navigation Dataset—0
Second-order Democratic Aggregation—0
Deep Learned Full-3D Object Completion from Single View—0
Learning Monocular Depth by Distilling Cross-domain Stereo NetworksCode0
Holistic 3D Scene Parsing and Reconstruction from a Single RGB ImageCode0
Parsing Geometry Using Structure-Aware Shape TemplatesCode0
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding—0
A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators—0
Unified Perceptual Parsing for Scene UnderstandingCode1
A Reinforcement Learning Approach to Target Tracking in a Camera Network—0
Three for one and one for three: Flow, Segmentation, and Surface NormalsCode0
In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization—0
Show:102550
← PrevPage 61 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