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 801–850 of 1723 papers

TitleStatusHype
AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis—0
Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring—0
Egocentric Activity Recognition and Localization on a 3D Map—0
Efficient Point Transformer for Large-scale 3D Scene Understanding—0
A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance—0
Efficient Label Collection for Unlabeled Image Datasets—0
Efficient Interactive 3D Multi-Object Removal—0
CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting—0
CaDIS: Cataract Dataset for Image Segmentation—0
Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving—0
Efficient 3D Instance Mapping and Localization with Neural Fields—0
Real-time Semantic Segmentation with Context Aggregation Network—0
EarthNets: Empowering AI in Earth Observation—0
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding—0
BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding—0
Application of Multimodal Large Language Models in Autonomous Driving—0
AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning—0
3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer—0
360^ High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer—0
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM—0
Trajectory-based Scene Understanding using Dirichlet Process Mixture Model—0
BUTLER: Building Understanding in TextWorld via Language for Embodied Reasoning—0
Dynamic Scene Understanding from Vision-Language Representations—0
Building an Affordances Map with Interactive Perception—0
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving—0
Dynamic Clustering Transformer Network for Point Cloud Segmentation—0
A pooling based scene text proposal technique for scene text reading in the wild—0
DublinCity: Annotated LiDAR Point Cloud and its Applications—0
Bridging Scene Understanding and Task Execution with Flexible Simulation Environments—0
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection—0
DSNet: An Efficient CNN for Road Scene Segmentation—0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration—0
BOX3D: Lightweight Camera-LiDAR Fusion for 3D Object Detection and Localization—0
A Dataset for Semantic Segmentation in the Presence of Unknowns—0
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving—0
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models—0
DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder—0
Boundary Seeking GANs—0
APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation—0
DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving—0
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation—0
M2DA: Multi-Modal Fusion Transformer Incorporating Driver Attention for Autonomous Driving—0
Bottom-up Instance Segmentation using Deep Higher-Order CRFs—0
Anticipating Object State Changes in Long Procedural Videos—0
LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition—0
DORSal: Diffusion for Object-centric Representations of Scenes et al—0
Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding—0
DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation—0
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding—0
Show:102550
← PrevPage 17 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