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 201–225 of 1723 papers

TitleStatusHype
Transformers in Unsupervised Structure-from-MotionCode1
Simple Image-level Classification Improves Open-vocabulary Object DetectionCode1
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D EnvironmentsCode1
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object DetectionCode1
Language Embedded 3D Gaussians for Open-Vocabulary Scene UnderstandingCode1
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene SegmentationCode1
Panoptic Video Scene Graph GenerationCode1
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense KnowledgeCode1
TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene UnderstandingCode1
NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph EnrichmentCode1
TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in RainCode1
TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic SegmentationCode1
Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous DrivingCode1
Multimodal Dataset for Localization, Mapping and Crop Monitoring in Citrus Tree FarmsCode1
PanopticNDT: Efficient and Robust Panoptic MappingCode1
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic DataCode1
Mask4D: End-to-End Mask-Based 4D Panoptic Segmentation for LiDAR SequencesCode1
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D ScansCode1
Multi3DRefer: Grounding Text Description to Multiple 3D ObjectsCode1
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense CaptioningCode1
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal TargetsCode1
Understanding Dark Scenes by Contrasting Multi-Modal ObservationsCode1
Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture RecognitionCode1
Vision Relation Transformer for Unbiased Scene Graph GenerationCode1
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous DrivingCode1
Show:102550
← PrevPage 9 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