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 1351–1400 of 1723 papers

TitleStatusHype
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation—0
Cross-modal Learning for Multi-modal Video Categorization—0
An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice—0
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single ImageCode1
Shallow2Deep: Indoor Scene Modeling by Single Image Understanding—0
3D Gated Recurrent Fusion for Semantic Scene Completion—0
Exploiting Temporal Coherence for Multi-modal Video Categorization—0
Image Segmentation Using Deep Learning: A SurveyCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation—0
Visual-Semantic Graph Attention Networks for Human-Object Interaction DetectionCode1
Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation—0
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images—0
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal EstimationCode1
DADA: Driver Attention Prediction in Driving Accident ScenariosCode0
AeroRIT: A New Scene for Hyperspectral Image AnalysisCode1
Inferring Distributions Over Depth from a Single ImageCode0
CNN-based Lidar Point Cloud De-Noising in Adverse WeatherCode0
Deep Learning based Switching Filter for Impulsive Noise Removal in Color ImagesCode0
Scene recognition based on DNN and game theory with its applications in human-robot interaction—0
Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object RepresentationsCode0
TextSLAM: Visual SLAM with Planar Text FeaturesCode1
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANCode1
Language-based Colorization of Scene SketchesCode0
Knowledge Distillation for Incremental Learning in Semantic Segmentation—0
Algorithmic Design and Implementation of Unobtrusive Multistatic Serial LiDAR Image—0
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion FramesCode1
PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation—0
Addressing the Sim2Real Gap in Robotic 3D Object Classification—0
Leveraging Auxiliary Text for Deep Recognition of Unseen Visual Relationships—0
GANspection—0
Deep Contextual Attention for Human-Object Interaction Detection—0
Deep Semantic Segmentation of Natural and Medical Images: A Review—0
Semantic Understanding of Foggy Scenes with Purely Synthetic DataCode0
Using Image Priors to Improve Scene Understanding—0
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency DetectionCode0
Real-Time Semantic Stereo Matching—0
Multi-view PointNet for 3D Scene Understanding—0
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving—0
Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation—0
On the Pareto Efficiency of Quantized CNN—0
Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression—0
Underwater Image Super-Resolution using Deep Residual MultipliersCode1
Pose-aware Multi-level Feature Network for Human Object Interaction DetectionCode0
Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition—0
Multi-Task Learning for Automotive Foggy Scene Understanding via Domain Adaptation to an Illumination-Invariant Representation—0
Visuomotor Understanding for Representation Learning of Driving Scenes—0
Global Aggregation then Local Distribution in Fully Convolutional NetworksCode1
Semantic Foreground Inpainting from Weak SupervisionCode0
DublinCity: Annotated LiDAR Point Cloud and its Applications—0
Show:102550
← PrevPage 28 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