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 601–650 of 1723 papers

TitleStatusHype
Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational TransformersCode1
Digital Divides in Scene Recognition: Uncovering Socioeconomic Biases in Deep Learning Systems—0
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents—0
UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature RepresentationCode1
S^3M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving—0
Pixel-Wise Recognition for Holistic Surgical Scene UnderstandingCode2
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection—0
ICGNet: A Unified Approach for Instance-Centric GraspingCode0
GARField: Group Anything with Radiance FieldsCode3
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding—0
RSUD20K: A Dataset for Road Scene Understanding In Autonomous DrivingCode1
Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization—0
Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation—0
Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection—0
VLP: Vision Language Planning for Autonomous Driving—0
FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the WildCode0
3DMIT: 3D Multi-modal Instruction Tuning for Scene UnderstandingCode1
FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding—0
Unsupervised 3D Structure Inference from Category-Specific Image Collections—0
When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach—0
Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness—0
PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular VideoCode0
Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and ConsistencyCode0
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene UnderstandingCode2
SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes—0
Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models—0
Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding—0
Robust Multi-Modal Image Stitching for Improved Scene Understanding—0
Cloud-Device Collaborative Learning for Multimodal Large Language Models—0
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object DetectionCode1
WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural EnvironmentsCode1
Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarizationCode1
BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions—0
Object Attribute Matters in Visual Question AnsweringCode0
AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model—0
Language-Assisted 3D Scene Understanding—0
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask GuidanceCode1
Simple Image-level Classification Improves Open-vocabulary Object DetectionCode1
Transformers in Unsupervised Structure-from-MotionCode1
Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment—0
VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding—0
Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis—0
Zoom in on the Plant: Fine-grained Analysis of Leaf, Stem and Vein InstancesCode0
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D EnvironmentsCode1
Chat-Scene: Bridging 3D Scene and Large Language Models with Object IdentifiersCode2
X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge TransferCode0
Spatiotemporal Event Graphs for Dynamic Scene Understanding—0
SkyScenes: A Synthetic Dataset for Aerial Scene Understanding—0
Cataract-1K: Cataract Surgery Dataset for Scene Segmentation, Phase Recognition, and Irregularity Detection—0
Show:102550
← PrevPage 13 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