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 751–800 of 1723 papers

TitleStatusHype
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual ImpairmentsCode1
DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous VehicleCode0
The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context DatasetCode1
Smart Infrastructure: A Research Junction—0
CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic SurgeryCode1
Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation—0
PSDR-Room: Single Photo to Scene using Differentiable Rendering—0
Towards accurate instance segmentation in large-scale LiDAR point cloudsCode1
Object Recognition System on a Tactile Device for Visually Impaired—0
AVSegFormer: Audio-Visual Segmentation with TransformerCode1
Artifacts Mapping: Multi-Modal Semantic Mapping for Object Detection and 3D Localization—0
Towards Open Vocabulary Learning: A SurveyCode2
Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many SynthesisCode0
Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos—0
Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties—0
SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV FusionCode1
Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation—0
OpenMask3D: Open-Vocabulary 3D Instance SegmentationCode2
Semantic-aware Transmission for Robust Point Cloud Classification—0
Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape PriorCode1
CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation—0
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic SegmentationCode1
Estimating Generic 3D Room Structures from 2D AnnotationsCode1
DORSal: Diffusion for Object-centric Representations of Scenes et al—0
Neural Projection Mapping Using Reflectance Fields—0
SNeL: A Structured Neuro-Symbolic Language for Entity-Based Multimodal Scene Understanding—0
SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic UnderstandingCode1
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene UnderstandingCode2
TopoMask: Instance-Mask-Based Formulation for the Road Topology Problem via Transformer-Based Architecture—0
A Dynamic Feature Interaction Framework for Multi-task Visual Perception—0
Towards Label-free Scene Understanding by Vision Foundation ModelsCode1
Disaster Anomaly Detector via Deeper FCDDs for Explainable Initial Responses—0
Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing—0
Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes—0
Towards In-context Scene UnderstandingCode1
Self-supervised Vision Transformers for 3D Pose Estimation of Novel ObjectsCode0
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color ContrastCode1
Dynamic Clustering Transformer Network for Point Cloud Segmentation—0
Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph GenerationCode0
Multi-Scale Attention for Audio Question AnsweringCode1
Robust Category-Level 3D Pose Estimation from Synthetic Data—0
Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments—0
Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual ScenariosCode0
PanoContext-Former: Panoramic Total Scene Understanding with a Transformer—0
Generating Visual Spatial Description via Holistic 3D Scene UnderstandingCode1
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding—0
TextSLAM: Visual SLAM with Semantic Planar Text FeaturesCode2
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene GraphsCode0
MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning—0
Show:102550
← PrevPage 16 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