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 1131–1140 of 1723 papers

Title	Date	Tasks	Status	Hype
Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images	Aug 6, 2021	Depth EstimationPanoptic Segmentation	CodeCode Available	1
Interpretable Visual Understanding with Cognitive Attention Network	Aug 6, 2021	Scene UnderstandingVisual Commonsense Reasoning	CodeCode Available	0
From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection	Jul 30, 2021	3D Object Detectionobject-detection	CodeCode Available	1
CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation	Jul 29, 2021	Depth EstimationMonocular Depth Estimation	—Unverified	0
Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel Dataset	Jul 27, 2021	Scene Text RecognitionScene Understanding	CodeCode Available	1
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation	Jul 25, 2021	Active LearningDeep Learning	CodeCode Available	1
Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation	Jul 23, 2021	Domain AdaptationFew-Shot Learning	CodeCode Available	1
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds	Jul 23, 2021	Point Cloud SegmentationScene Understanding	—Unverified	0
Photon-Starved Scene Inference using Single Photon Cameras	Jul 23, 2021	Depth Estimationimage-classification	CodeCode Available	1
Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation	Jul 21, 2021	Image Segmentationobject-detection	CodeCode Available	0

Show:10 25 50

← PrevPage 114 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