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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1361–1370 of 1723 papers

Title	Date	Tasks	Status	Hype
Visual-Semantic Graph Attention Networks for Human-Object Interaction Detection	Jan 7, 2020	Graph AttentionHuman-Object Interaction Detection	CodeCode Available	1
Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation	Jan 6, 2020	3D Instance SegmentationInstance Segmentation	—Unverified	0
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images	Dec 25, 2019	Scene UnderstandingSegmentation	—Unverified	0
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation	Dec 20, 2019	Disparity EstimationScene Understanding	CodeCode Available	1
DADA: Driver Attention Prediction in Driving Accident Scenarios	Dec 18, 2019	Driver Attention MonitoringPrediction	CodeCode Available	0
AeroRIT: A New Scene for Hyperspectral Image Analysis	Dec 17, 2019	Hyperspectral image analysisImage Super-Resolution	CodeCode Available	1
Inferring Distributions Over Depth from a Single Image	Dec 12, 2019	Autonomous VehiclesBinary Classification	CodeCode Available	0
CNN-based Lidar Point Cloud De-Noising in Adverse Weather	Dec 9, 2019	Autonomous VehiclesScene Understanding	CodeCode Available	0
Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images	Dec 3, 2019	DenoisingImage Denoising	CodeCode Available	0
Scene recognition based on DNN and game theory with its applications in human-robot interaction	Dec 3, 2019	Image RegistrationScene Recognition	—Unverified	0

Show:10 25 50

← PrevPage 137 of 173Next →

All datasets Semantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K val Semantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.44	—	Unverified
2	Team VGAI (TCS Research)	OMQ	0.37	—	Unverified
3	Demo_semantic_SLAM	OMQ	0.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CPN(ResNet-101)	Mean IoU	46.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.35	—	Unverified