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 1001–1025 of 1723 papers

TitleStatusHype
MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding—0
P3Depth: Monocular Depth Estimation with a Piecewise Planarity PriorCode1
BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationCode2
Online panoptic 3D reconstruction as a Linear Assignment ProblemCode1
Point Scene Understanding via Disentangled Instance Mesh ReconstructionCode1
Collaborative Transformers for Grounded Situation RecognitionCode1
Multi-Task Learning for Visual Scene Understanding—0
Learning to Answer Questions in Dynamic Audio-Visual ScenariosCode1
Semi-supervised and Deep learning Frameworks for Video Classification and Key-frame Identification—0
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering—0
Self-Supervised Road Layout Parsing with Graph Auto-EncodingCode0
Towards 3D Scene Understanding by Referring Synthetic Models—0
Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows—0
Deep Point Cloud Simplification for High-quality Surface Reconstruction—0
MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question AnsweringCode1
Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans—0
WeakM3D: Towards Weakly Supervised Monocular 3D Object DetectionCode1
Deep learning for radar data exploitation of autonomous vehicleCode1
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry—0
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with TransformersCode2
On Steering Multi-Annotations per Sample for Multi-Task Learning—0
Fast Neural Architecture Search for Lightweight Dense Prediction Networks—0
Hybrid Optimized Deep Convolution Neural Network based Learning Model for Object Detection—0
Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic SegmentationCode1
Show:102550
← PrevPage 41 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