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 1401–1450 of 1723 papers

TitleStatusHype
Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense—0
Texture Underfitting for Domain Adaptation—0
Dynamic Graph Message Passing NetworksCode1
Rotation Invariant Convolutions for 3D Point Clouds Deep LearningCode0
RIO: 3D Object Instance Re-Localization in Changing Indoor EnvironmentsCode0
To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation—0
VideoNavQA: Bridging the Gap between Visual and Embodied Question AnsweringCode1
Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes—0
Object as Distribution—0
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and ClassificationCode0
Improving Social Awareness Through DANTE: A Deep Affinity Network for Clustering Conversational InteractantsCode0
SDNet: Semantically Guided Depth Estimation Network—0
U4D: Unsupervised 4D Dynamic Scene Understanding—0
Temporally Consistent Horizon LinesCode0
M3D-RPN: Monocular 3D Region Proposal Network for Object DetectionCode1
Structure-Aware Residual Pyramid Network for Monocular Depth EstimationCode0
Preferences Prediction using a Gallery of Mobile Device based on Scene Recognition and Object DetectionCode0
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation NetworkCode1
CaDIS: Cataract Dataset for Image Segmentation—0
Loss Switching Fusion with Similarity Search for Video ClassificationCode0
Active Scene Understanding via Online Semantic Reconstruction—0
Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes—0
RailSem19: A Dataset for Semantic Rail Scene Understanding—0
Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding—0
A New Ratio Image Based CNN Algorithm For SAR Despeckling—0
Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding—0
Panoptic Edge Detection—0
Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera—0
Learning to Detect Human-Object Interactions With Knowledge—0
Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachCode0
Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation—0
Distraction-Aware Shadow Detection—0
Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation—0
OK-VQA: A Visual Question Answering Benchmark Requiring External KnowledgeCode1
Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from VideoCode0
Implicit Background Estimation for Semantic SegmentationCode0
Real-time Approximate Bayesian Computation for Scene Understanding—0
Spatial Sampling Network for Fast Scene Understanding—0
Bridging Stereo Matching and Optical Flow via Spatiotemporal CorrespondenceCode0
Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial ImagesCode0
A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling—0
Reasoning About Physical Interactions with Object-Centric Models—0
An Information-Theoretic Metric of Transferability for Task Transfer LearningCode0
Segmenting the FutureCode0
DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation—0
Deep Optics for Monocular Depth Estimation and 3D Object Detection—0
DSNet: An Efficient CNN for Road Scene Segmentation—0
Deep Surface Normal Estimation with Hierarchical RGB-D FusionCode0
Structured agents for physical construction—0
GFF: Gated Fully Fusion for Semantic SegmentationCode1
Show:102550
← PrevPage 29 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