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 901–950 of 1723 papers

TitleStatusHype
Distillation of Human-Object Interaction Contexts for Action Recognition—0
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features—0
Distraction-Aware Shadow Detection—0
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos—0
Do Deep Neural Networks Model Nonlinear Compositionality in the Neural Representation of Human-Object Interactions?—0
Does CLIP perceive art the same way we do?—0
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs—0
DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation—0
DORSal: Diffusion for Object-centric Representations of Scenes et al—0
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation—0
DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving—0
DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder—0
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models—0
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving—0
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration—0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
DSNet: An Efficient CNN for Road Scene Segmentation—0
DublinCity: Annotated LiDAR Point Cloud and its Applications—0
Dynamic Clustering Transformer Network for Point Cloud Segmentation—0
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving—0
Dynamic Scene Understanding from Vision-Language Representations—0
Trajectory-based Scene Understanding using Dirichlet Process Mixture Model—0
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM—0
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding—0
EarthNets: Empowering AI in Earth Observation—0
Efficient 3D Instance Mapping and Localization with Neural Fields—0
Efficient Interactive 3D Multi-Object Removal—0
Efficient Label Collection for Unlabeled Image Datasets—0
Efficient Point Transformer for Large-scale 3D Scene Understanding—0
Egocentric Activity Recognition and Localization on a 3D Map—0
Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring—0
EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting—0
EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting—0
Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception—0
Embodied Scene Understanding for Vision Language Models via MetaVQA—0
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding—0
Embodied Visual Active Learning for Semantic Segmentation—0
EmbRACE-3K: Embodied Reasoning and Action in Complex Environments—0
Embracing Diffraction: A Paradigm Shift in Wireless Sensing and Communication—0
EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction—0
Empowering cyberphysical systems of systems with intelligence—0
Empowering Large Language Models with 3D Situation Awareness—0
Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision—0
End-to-end Autonomous Driving using Deep Learning: A Systematic Review—0
End-to-End Race Driving with Deep Reinforcement Learning—0
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds—0
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding—0
Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning—0
Enhancing image captioning with depth information using a Transformer-based framework—0
Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors—0
Show:102550
← PrevPage 19 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