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 1651–1700 of 1723 papers

TitleStatusHype
A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding—0
Deep Structured Scene Parsing by Learning with Image Descriptions—0
The Cityscapes Dataset for Semantic Urban Scene UnderstandingCode1
Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images—0
Attend, Infer, Repeat: Fast Scene Understanding with Generative ModelsCode0
Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance—0
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding—0
A diffusion and clustering-based approach for finding coherent motions and understanding crowd scenes—0
What Can I Do Around Here? Deep Functional Scene Understanding for Cognitive Robots—0
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesCode0
Car Segmentation and Pose Estimation using 3D Object Models—0
Single Image 3D Without a Single 3D Image—0
Pedestrian Travel Time Estimation in Crowded Scenes—0
Exploiting High Level Scene Cues in Stereo Reconstruction—0
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation—0
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning—0
SceneNet: Understanding Real World Indoor Scenes With Synthetic DataCode0
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer—0
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene UnderstandingCode1
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationCode1
Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks—0
Semantic Pose using Deep Networks Trained on Synthetic RGB-D—0
Discovery of Shared Semantic Spaces for Multi-Scene Video Query and Summarization—0
Lifting GIS Maps into Strong Geometric Context for Scene Understanding—0
Visual Vibrometry: Estimating Material Properties From Small Motion in Video—0
Efficient Label Collection for Unlabeled Image Datasets—0
SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite—0
Picture: A Probabilistic Programming Language for Scene Perception—0
Joint SFM and Detection Cues for Monocular 3D Localization in Road Scenes—0
Holistic 3D Scene Understanding From a Single Geo-Tagged Image—0
Deeply Learned Attributes for Crowded Scene Understanding—0
Understanding Pedestrian Behaviors From Stationary Crowd Groups—0
Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models—0
Learning to Interpret and Describe Abstract Scenes—0
SynthCam3D: Semantic Understanding With Synthetic Indoor Scenes—0
Semantic Motion Segmentation Using Dense CRF Formulation—0
The toulouse vanishing points dataset—0
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding—0
Data-Driven Scene Understanding with Adaptively Retrieved Exemplars—0
Towards Scene Understanding with Detailed 3D Object Representations—0
Designing Deep Networks for Surface Normal Estimation—0
Scene Image is Non-Mutually Exclusive - A Fuzzy Qualitative Scene Understanding—0
Fusion Based Holistic Road Scene Understanding—0
Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding—0
Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects—0
Looking Beyond the Visible Scene—0
Scene-Independent Group Profiling in Crowd—0
An Exemplar-based CRF for Multi-instance Object Segmentation—0
Incorporating Scene Context and Object Layout into Appearance Modeling—0
Microsoft COCO: Common Objects in ContextCode1
Show:102550
← PrevPage 34 of 35Next →
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