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 1101–1150 of 1723 papers

TitleStatusHype
Semantic Segmentation-assisted Scene Completion for LiDAR Point CloudsCode1
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal EstimationCode1
Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction—0
Label-Attention Transformer with Geometrically Coherent Objects for Image CaptioningCode0
Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images—0
On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation—0
PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point CloudsCode1
Residual 3D Scene Flow Learning with Context-Aware Feature Extraction—0
Single Image 3D Object Estimation with Primitive Graph NetworksCode0
RefineCap: Concept-Aware Refinement for Image Captioning—0
Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and TrackingCode2
Improving Building Segmentation for Off-Nadir Satellite Imagery—0
Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds—0
Spatio-temporal Self-Supervised Representation Learning for 3D Point CloudsCode1
From General to Specific: Informative Scene Graph Generation via Balance AdjustmentCode1
Multi-task learning from fixed-wing UAV images for 2D/3D city modeling—0
DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based OptimizationCode1
Deep Bayesian Image Set Classification: A Defence Approach against Adversarial Attacks—0
ODAM: Object Detection, Association, and Mapping using Posed RGB VideoCode1
A Multiple-View Geometric Model for Specularity Prediction on General Curved Surfaces—0
Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image—0
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor ScenesCode0
Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization—0
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksCode1
A Hybrid Sparse-Dense Monocular SLAM System for Autonomous DrivingCode1
Indoor Semantic Scene Understanding using Multi-modality Fusion—0
UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial AttacksCode0
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionCode1
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos—0
One-Shot Object Affordance Detection in the WildCode1
Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View ImagesCode1
Interpretable Visual Understanding with Cognitive Attention NetworkCode0
From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object DetectionCode1
CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation—0
Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel DatasetCode1
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic SegmentationCode1
Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report GenerationCode1
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds—0
Photon-Starved Scene Inference using Single Photon CamerasCode1
Weighted Intersection over Union (wIoU) for Evaluating Image SegmentationCode0
Generative Video Transformer: Can Objects be the Words?—0
Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems—0
CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations—0
DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference—0
SynPick: A Dataset for Dynamic Bin Picking Scene UnderstandingCode1
A Weakly-Supervised Depth Estimation Network Using Attention Mechanism—0
Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance VotingCode0
Empowering cyberphysical systems of systems with intelligence—0
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface—0
Cognitive Visual Commonsense Reasoning Using Dynamic Working MemoryCode0
Show:102550
← PrevPage 23 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